pylearn: pylearn/algorithms/mcRBM.py annotate

annotate pylearn/algorithms/mcRBM.py @ 1000:d4a14c6c36e0

mcRBM - post code-review #1 with Guillaume

author	James Bergstra <bergstrj@iro.umontreal.ca>
date	Tue, 24 Aug 2010 19:24:54 -0400
parents	c6d08a760960
children	075c193afd1b

rev	line source
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	1 """
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	2 This file implements the Mean & Covariance RBM discussed in
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	3
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	4 Ranzato, M. and Hinton, G. E. (2010)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	5 Modeling pixel means and covariances using factored third-order Boltzmann machines.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	6 IEEE Conference on Computer Vision and Pattern Recognition.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	7
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	8 and performs one of the experiments on CIFAR-10 discussed in that paper. There are some minor
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	9 discrepancies between the paper and the accompanying code (train_mcRBM.py), and the
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	10 accompanying code has been taken to be correct in those cases because I couldn't get things to
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	11 work otherwise.
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	12
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	13
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	14 Math
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	15 ====
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	16
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	17 Energy of "covariance RBM"
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	18
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	19 E = -0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i C_{if} v_i )^2
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	20 = -0.5 \sum_f (\sum_k P_{fk} h_k) ( \sum_i C_{if} v_i )^2
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	21 "vector element f" "vector element f"
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	22
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	23 In some parts of the paper, the P matrix is chosen to be a diagonal matrix with non-positive
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	24 diagonal entries, so it is helpful to see this as a simpler equation:
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	25
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	26 E = \sum_f h_f ( \sum_i C_{if} v_i )^2
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	27
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	28
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	29
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	30 Version in paper
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	31 ----------------
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	32
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	33 Full Energy of the Mean and Covariance RBM, with
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	34 :math:`h_k = h_k^{(c)}`,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	35 :math:`g_j = h_j^{(m)}`,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	36 :math:`b_k = b_k^{(c)}`,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	37 :math:`c_j = b_j^{(m)}`,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	38 :math:`U_{if} = C_{if}`,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	39
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	40 E (v, h, g) =
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	41 - 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i (U_{if} v_i) / \|U_{.f}\|*\|v\| )^2
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	42 - \sum_k b_k h_k
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	43 + 0.5 \sum_i v_i^2
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	44 - \sum_j \sum_i W_{ij} g_j v_i
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	45 - \sum_j c_j g_j
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	46
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	47 For the energy function to correspond to a probability distribution, P must be non-positive. P
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	48 is initialized to be a diagonal, and in our experience it can be left as such because even in
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	49 the paper it has a very low learning rate, and is only allowed to be updated after the filters
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	50 in U are learned (in effect).
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	51
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	52 Version in published train_mcRBM code
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	53 -------------------------------------
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	54
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	55 The train_mcRBM file implements learning in a similar but technically different Energy function:
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	56
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	57 E (v, h, g) =
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	58 - 0.5 \sum_f \sum_k P_{fk} h_k (\sum_i U_{if} v_i / sqrt(\sum_i v_i^2/I + 0.5))^2
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	59 - \sum_k b_k h_k
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	60 + 0.5 \sum_i v_i^2
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	61 - \sum_j \sum_i W_{ij} g_j v_i
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	62 - \sum_j c_j g_j
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	63
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	64 There are two differences with respect to the paper:
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	65
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	66 - 'v' is not normalized by its length, but rather it is normalized to have length close to
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	67 the square root of the number of its components. The variable called 'small' that
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	68 "avoids division by zero" is orders larger than machine precision, and is on the order of
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	69 the normalized sum-of-squares, so I've included it in the Energy function.
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	70
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	71 - 'U' is also not normalized by its length. U is initialized to have columns that are
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	72 shorter than unit-length (approximately 0.2 with the 105 principle components in the
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	73 train_mcRBM data). During training, the columns of U are constrained manually to have
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	74 equal lengths (see the use of normVF), but Euclidean norm is allowed to change. During
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	75 learning it quickly converges towards 1 and then exceeds 1. It does not seem like this
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	76 column-wise normalization of U is justified by maximum-likelihood, I have no intuition
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	77 for why it is used.
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	78
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	79
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	80 Version in this code
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	81 --------------------
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	82
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	83 This file implements the same algorithm as the train_mcRBM code, except that the P matrix is
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	84 omitted for clarity, and replaced analytically with a negative identity matrix.
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	85
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	86 E (v, h, g) =
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	87 + 0.5 \sum_k h_k (\sum_i U_{ik} v_i / sqrt(\sum_i v_i^2/I + 0.5))^2
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	88 - \sum_k b_k h_k
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	89 + 0.5 \sum_i v_i^2
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	90 - \sum_j \sum_i W_{ij} g_j v_i
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	91 - \sum_j c_j g_j
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	92
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	93
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	94
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	95 Conventions in this file
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	96 ========================
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	97
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	98 This file contains some global functions, as well as a class (MeanCovRBM) that makes using them a little
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	99 more convenient.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	100
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	101
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	102 Global functions like `free_energy` work on an mcRBM as parametrized in a particular way.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	103 Suppose we have
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	104 I input dimensions,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	105 F squared filters,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	106 J mean variables, and
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	107 K covariance variables.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	108 The mcRBM is parametrized by 5 variables:
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	109
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	110 - `U`, a matrix whose rows are visible covariance directions (I x F)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	111 - `W`, a matrix whose rows are visible mean directions (I x J)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	112 - `b`, a vector of hidden covariance biases (K)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	113 - `c`, a vector of hidden mean biases (J)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	114
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	115 Matrices are generally layed out and accessed according to a C-order convention.
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	116
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	117 """
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	118
984 5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	119 #
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	120 # WORKING NOTES
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	121 # THIS DERIVATION IS BASED ON THE PAPER ENERGY FUNCTION
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	122 # NOT THE ENERGY FUNCTION IN THE CODE!!!
5badf36a6daf mcRBM - added notes to leading comment James Bergstra <bergstrj@iro.umontreal.ca> parents: 979 diff changeset	123 #
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	124 # Free energy is the marginal energy of visible units
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	125 # Recall:
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	126 # Q(x) = exp(-E(x))/Z ==> -log(Q(x)) - log(Z) = E(x)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	127 #
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	128 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	129 # E (v, h, g) =
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	130 # - 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / \|U_{*f}\|^2 \|v\|^2
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	131 # - \sum_k b_k h_k
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	132 # + 0.5 \sum_i v_i^2
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	133 # - \sum_j \sum_i W_{ij} g_j v_i
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	134 # - \sum_j c_j g_j
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	135 # - \sum_i a_i v_i
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	136 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	137 #
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	138 # Derivation, in which partition functions are ignored.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	139 #
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	140 # E(v) = -\log(Q(v))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	141 # = -\log( \sum_{h,g} Q(v,h,g))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	142 # = -\log( \sum_{h,g} exp(-E(v,h,g)))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	143 # = -\log( \sum_{h,g} exp(-
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	144 # - 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (\|U_{f}\| \|v\|)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	145 # - \sum_k b_k h_k
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	146 # + 0.5 \sum_i v_i^2
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	147 # - \sum_j \sum_i W_{ij} g_j v_i
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	148 # - \sum_j c_j g_j
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	149 # - \sum_i a_i v_i ))
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	150 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	151 # Get rid of double negs in exp
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	152 # = -\log( \sum_{h} exp(
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	153 # + 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (\|U_{f}\| \|v\|)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	154 # + \sum_k b_k h_k
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	155 # - 0.5 \sum_i v_i^2
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	156 # ) * \sum_{g} exp(
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	157 # + \sum_j \sum_i W_{ij} g_j v_i
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	158 # + \sum_j c_j g_j))
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	159 # - \sum_i a_i v_i
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	160 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	161 # Break up log
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	162 # = -\log( \sum_{h} exp(
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	163 # + 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (\|U_{f}\|\|v\|)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	164 # + \sum_k b_k h_k
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	165 # ))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	166 # -\log( \sum_{g} exp(
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	167 # + \sum_j \sum_i W_{ij} g_j v_i
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	168 # + \sum_j c_j g_j )))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	169 # + 0.5 \sum_i v_i^2
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	170 # - \sum_i a_i v_i
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	171 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	172 # Use domain h is binary to turn log(sum(exp(sum...))) into sum(log(..
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	173 # = -\log(\sum_{h} exp(
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	174 # + 0.5 \sum_f \sum_k P_{fk} h_k ( \sum_i U_{if} v_i )^2 / (\|U_{f}\| \|v\|)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	175 # + \sum_k b_k h_k
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	176 # ))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	177 # - \sum_{j} \log(1 + exp(\sum_i W_{ij} v_i + c_j ))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	178 # + 0.5 \sum_i v_i^2
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	179 # - \sum_i a_i v_i
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	180 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	181 # = - \sum_{k} \log(1 + exp(b_k + 0.5 \sum_f P_{fk}( \sum_i U_{if} v_i )^2 / (\|U_{f}\|\|v\|)))
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	182 # - \sum_{j} \log(1 + exp(\sum_i W_{ij} v_i + c_j ))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	183 # + 0.5 \sum_i v_i^2
972 0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	184 # - \sum_i a_i v_i
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	185 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	186 # For negative-one-diagonal P this gives:
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	187 #
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	188 # = - \sum_{k} \log(1 + exp(b_k - 0.5 \sum_i (U_{ik} v_i )^2 / (\|U_{k}\|\|v\|)))
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	189 # - \sum_{j} \log(1 + exp(\sum_i W_{ij} v_i + c_j ))
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	190 # + 0.5 \sum_i v_i^2
0b392d1401c5 mcRBM - adding math and comments James Bergstra <bergstrj@iro.umontreal.ca> parents: 967 diff changeset	191 # - \sum_i a_i v_i
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	192
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	193 import sys, os, logging
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	194 import numpy as np
973 aa201f357d7b mcRBM - added numpy import James Bergstra <bergstrj@iro.umontreal.ca> parents: 972 diff changeset	195 import numpy
988 fd243cb2bf0b mcRBM - moved some things to the top of the file James Bergstra <bergstrj@iro.umontreal.ca> parents: 987 diff changeset	196
fd243cb2bf0b mcRBM - moved some things to the top of the file James Bergstra <bergstrj@iro.umontreal.ca> parents: 987 diff changeset	197 import theano
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	198 from theano import function, shared, dot
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	199 from theano import tensor as TT
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	200 floatX = theano.config.floatX
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	201
988 fd243cb2bf0b mcRBM - moved some things to the top of the file James Bergstra <bergstrj@iro.umontreal.ca> parents: 987 diff changeset	202 import pylearn
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	203 #TODO: clean up the HMC_sampler code
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	204 #TODO: think of naming convention for acronyms + suffix?
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	205 from pylearn.sampling.hmc import HMC_sampler
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	206 from pylearn.io import image_tiling
999 c6d08a760960 added sgd_updates to gd/sgd.py. Modif mcRBM to use it. James Bergstra <bergstrj@iro.umontreal.ca> parents: 998 diff changeset	207 from pylearn.gd.sgd import sgd_updates
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	208 import pylearn.dataset_ops.image_patches
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	209
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	210 ###########################################
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	211 #
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	212 # Candidates for factoring
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	213 #
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	214 ###########################################
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	215
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	216 #TODO: Document, move to pylearn's math lib
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	217 def l1(X):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	218 return abs(X).sum()
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	219
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	220 #TODO: Document, move to pylearn's math lib
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	221 def l2(X):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	222 return TT.sqrt((X**2).sum())
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	223
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	224 #TODO: Document, move to pylearn's math lib
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	225 def contrastive_cost(free_energy_fn, pos_v, neg_v):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	226 return (free_energy_fn(pos_v) - free_energy_fn(neg_v)).sum()
988 fd243cb2bf0b mcRBM - moved some things to the top of the file James Bergstra <bergstrj@iro.umontreal.ca> parents: 987 diff changeset	227
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	228 #TODO: Typical use of contrastive_cost is to later use tensor.grad, but in that case we want to
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	229 # block gradient going through neg_v
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	230 def contrastive_grad(free_energy_fn, pos_v, neg_v, params, other_cost=0):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	231 """
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	232 :param pos_v: positive-phase sample of visible units
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	233 :param neg_v: negative-phase sample of visible units
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	234 """
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	235 #block the grad through neg_v
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	236 cost=contrastive_cost(free_energy_fn, pos_v, neg_v)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	237 if other_cost:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	238 cost = cost + other_cost
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	239 return theano.tensor.grad(cost,
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	240 wrt=params,
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	241 consider_constant=[neg_v])
973 aa201f357d7b mcRBM - added numpy import James Bergstra <bergstrj@iro.umontreal.ca> parents: 972 diff changeset	242
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	243 ###########################################
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	244 #
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	245 # Expressions that are mcRBM-specific
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	246 #
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	247 ###########################################
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	248
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	249 #TODO: make global function to initialize parameter
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	250
989 9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	251 def hidden_cov_units_preactivation_given_v(rbm, v, small=0.5):
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	252 """Return argument to the sigmoid that would give mean of covariance hid units
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	253
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	254 See the math at the top of this file for what 'adjusted' means.
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	255
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	256 return b - 0.5 * dot(adjusted(v), U)**2
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	257 """
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	258 (U,W,a,b,c) = rbm
989 9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	259 unit_v = v / (TT.sqrt(TT.mean(v**2, axis=1)+small)).dimshuffle(0,'x') # adjust row norm
9e753ddcc320 mcRBM - cleaned up the preactivation function James Bergstra <bergstrj@iro.umontreal.ca> parents: 988 diff changeset	260 return b - 0.5 * dot(unit_v, U)**2
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	261
992 30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	262 def free_energy_terms_given_v(rbm, v):
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	263 """Returns theano expression for the terms that are added to form the free energy of
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	264 visible vector `v` in an mcRBM.
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	265
992 30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	266 1. Free energy related to covariance hiddens
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	267 2. Free energy related to mean hiddens
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	268 3. Free energy related to L2-Norm of `v`
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	269 4. Free energy related to projection of `v` onto biases `a`
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	270 """
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	271 U, W, a, b, c = rbm
975 38e66e0da66a mcRBM - put softplus in directly for num. stability James Bergstra <bergstrj@iro.umontreal.ca> parents: 974 diff changeset	272 t0 = -TT.sum(TT.nnet.softplus(hidden_cov_units_preactivation_given_v(rbm, v)),axis=1)
38e66e0da66a mcRBM - put softplus in directly for num. stability James Bergstra <bergstrj@iro.umontreal.ca> parents: 974 diff changeset	273 t1 = -TT.sum(TT.nnet.softplus(c + dot(v,W)), axis=1)
38e66e0da66a mcRBM - put softplus in directly for num. stability James Bergstra <bergstrj@iro.umontreal.ca> parents: 974 diff changeset	274 t2 = 0.5 * TT.sum(v**2, axis=1)
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	275 t3 = -TT.dot(v, a)
992 30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	276 return [t0, t1, t2, t3]
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	277
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	278 def free_energy_given_v(rbm, v):
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	279 """Returns theano expression for free energy of visible vector `v` in an mcRBM
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	280 """
30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	281 return sum(free_energy_terms_given_v(rbm,v))
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	282
991 d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	283 def expected_h_g_given_v(rbm, v):
d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	284 """Returns tuple (`h`, `g`) of theano expression conditional expectations in an mcRBM.
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	285
991 d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	286 `h` is the conditional on the covariance units.
d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	287 `g` is the conditional on the mean units.
d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	288
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	289 """
991 d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	290 (U, W, a, b, c) = rbm
d68828c98c38 mcRBM - cleaned up expected hidden unit function James Bergstra <bergstrj@iro.umontreal.ca> parents: 990 diff changeset	291 h = TT.nnet.sigmoid(hidden_cov_units_preactivation_given_v(rbm, v))
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	292 g = nnet.sigmoid(c + dot(v,W))
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	293 return (h, g)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	294
996 60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	295 def n_visible_units(rbm):
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	296 """Return the number of visible units of this RBM
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	297
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	298 For an RBM made from shared variables, this will return an integer,
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	299 for a purely symbolic RBM this will return a theano expression.
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	300
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	301 """
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	302 W = rbm[1]
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	303 try:
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	304 return W.value.shape[0]
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	305 except AttributeError:
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	306 return W.shape[0]
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	307
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	308 def sampler(rbm, n_particles, n_visible=None, rng=7823748):
996 60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	309 """Return an `HMC_sampler` that will draw samples from the distribution over visible
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	310 units specified by this RBM.
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	311
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	312 :param n_particles: this many parallel chains will be simulated.
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	313 :param rng: seed or numpy RandomState object to initialize particles, and to drive the simulation.
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	314 """
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	315 if not hasattr(rng, 'randn'):
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	316 rng = np.random.RandomState(rng)
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	317 if n_visible is None:
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	318 n_visible = n_visible_units(rbm)
996 60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	319 rval = HMC_sampler(
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	320 positions = [shared(
996 60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	321 rng.randn(
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	322 n_particles,
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	323 n_visible).astype(floatX),
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	324 name='particles')],
996 60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	325 energy_fn = lambda p : free_energy_given_v(rbm, p[0]),
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	326 seed=int(rng.randint(2**30)))
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	327 return rval
60f279ec0f7f mcRBM - made sampler a global function James Bergstra <bergstrj@iro.umontreal.ca> parents: 995 diff changeset	328
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	329 #############################
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	330 #
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	331 # Convenient data container
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	332 #
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	333 #############################
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	334
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	335 class MeanCovRBM(object):
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	336 """Container for mcRBM parameters
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	337
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	338 It provides parameter lookup by name, as well as a heuristic for initializing the
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	339 parameters for effective learning.
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	340
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	341 Attributes:
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	342
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	343 - U - the covariance filters (theano shared variable)
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	344 - W - the mean filters (theano shared variable)
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	345 - a - the visible bias (theano shared variable)
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	346 - b - the covariance bias (theano shared variable)
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	347 - c - the mean bias (theano shared variable)
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	348
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	349 """
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	350
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	351 params = property(lambda s: [s.U, s.W, s.a, s.b, s.c])
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	352
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	353 n_visible = property(lambda s: s.W.value.shape[0])
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	354
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	355 def __init__(self, U, W, a, b, c):
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	356 self.__dict__.update(locals())
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	357 del self.__dict__['self']
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	358
997 71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	359 def __getitem__(self, idx):
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	360 # support unpacking of this container as if it were a tuple
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	361 return self.params[idx]
71b0132b694a mcRBM - removed container logic that was redundant with global methods James Bergstra <bergstrj@iro.umontreal.ca> parents: 996 diff changeset	362
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	363 @classmethod
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	364 def new_from_dims(cls, n_I, n_K, n_J, rng = 8923402190):
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	365 """
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	366 Return a MeanCovRBM instance with randomly-initialized parameters.
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	367
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	368 :param n_I: input dimensionality
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	369 :param n_K: number of covariance hidden units
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	370 :param n_J: number of mean filters (linear)
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	371 :param rng: seed or numpy RandomState object to initialize params
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	372 """
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	373 if not hasattr(rng, 'randn'):
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	374 rng = np.random.RandomState(rng)
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	375
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	376 def shrd(X,name):
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	377 return shared(X.astype(floatX), name=name)
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	378
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	379 # initialization taken from train_mcRBM.py
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	380 return cls(
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	381 U = shrd(0.02 * rng.randn(n_I, n_K),'U'),
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	382 W = shrd(0.05 * rng.randn(n_I, n_J),'W'),
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	383 a = shrd(np.ones(n_I)*(0),'a'),
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	384 b = shrd(np.ones(n_K)*2,'b'),
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	385 c = shrd(np.ones(n_J)*(-2),'c'))
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	386
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	387 def __getstate__(self):
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	388 # unpack shared containers, which may have references to Theano stuff and are not a
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	389 # long-term stable data type.
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	390 return dict(
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	391 U = self.U.value,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	392 W = self.W.value,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	393 b = self.b.value,
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	394 c = self.c.value)
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	395
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	396 def __setstate__(self, dct):
995 68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	397 d = dict(dct)
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	398 for key in ['U', 'W', 'a', 'b', 'c']:
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	399 d[key] = shared(d[key], name=key)
68ca3ea34e72 mcRBM - cleaned up new_from_dims James Bergstra <bergstrj@iro.umontreal.ca> parents: 994 diff changeset	400 self.__init__(**d)
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	401
90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	402
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	403 #TODO: put the normalization of U as a global function
967 90e11d5d0a41 adding algorithms/mcRBM, but it is not done yet James Bergstra <bergstrj@iro.umontreal.ca> parents: diff changeset	404
979 2a53384d9742 mcRBM - hacks to driver James Bergstra <bergstrj@iro.umontreal.ca> parents: 978 diff changeset	405
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	406 #TODO: put the learning loop as a global function or class, so that someone could load and TRAIN an mcRBM!!!
992 30b7c4defb6c mcRBM - it works and committing it is taking forever... lets try this approach James Bergstra <bergstrj@iro.umontreal.ca> parents: 991 diff changeset	407
1000 d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	408 if __name__ == '__main__':
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	409 import pylearn.algorithms.tests.test_mcRBM
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume James Bergstra <bergstrj@iro.umontreal.ca> parents: 999 diff changeset	410 pylearn.algorithms.tests.test_mcRBM.test_reproduce_ranzato_hinton_2010(as_unittest=True)

Mercurial > pylearn

annotate pylearn/algorithms/mcRBM.py @ 1000:d4a14c6c36e0