Mercurial > pylearn
annotate algorithms/layer.py @ 518:4aa7f74ea93f
init dataset
| author | James Bergstra <bergstrj@iro.umontreal.ca> |
|---|---|
| date | Wed, 12 Nov 2008 12:36:09 -0500 |
| parents | c7ce66b4e8f4 |
| children |
| rev | line source |
|---|---|
| 498 | 1 """ |
| 2 @todo: Make a layer class, with standardized names: | |
| 3 input, cost, lr, and update | |
| 4 (a Method called update, to be more precise, whose first argument is the input) | |
| 5 | |
|
503
c7ce66b4e8f4
Extensions to algorithms, and some cleanup (by defining linear_output result).
Joseph Turian <turian@gmail.com>
parents:
498
diff
changeset
|
6 input_dimension, output_dimension (aliased as nin and nout) |
|
c7ce66b4e8f4
Extensions to algorithms, and some cleanup (by defining linear_output result).
Joseph Turian <turian@gmail.com>
parents:
498
diff
changeset
|
7 |
| 498 | 8 Modules like pylearn.algorithms.logistic_regression.Module_Nclass and |
| 9 pylearn.algorithms.???.Bin_Regressor should inherit from Layer and | |
| 10 Stacker should assume Layer. | |
| 11 """ |