Mercurial > pylearn

annotate doc/v2_planning/requirements.txt @ 1117:c1943feada10

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Proposal for theano dataset wrapper. The details still have to be worked out.
author Arnaud Bergeron <abergeron@gmail.com>
date Tue, 14 Sep 2010 15:22:48 -0400
parents 4eda3f52ebef
children 1f5465622394
rev   line source
1093
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
1 ============
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
2 Requirements
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
3 ============
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
4
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
5
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
6 Application Requirements
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
7 ========================
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
8
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
9 Terminology and Abbreviations:
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
10 ------------------------------
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
11
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
12 MLA - machine learning algorithm
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
13
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
14 learning problem - a machine learning application typically characterized by a
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
15 dataset (possibly dataset folds) one or more functions to be learned from the
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
16 data, and one or more metrics to evaluate those functions. Learning problems
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
17 are the benchmarks for empirical model comparison.
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
18
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
19 n. of - number of
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
20
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
21 SGD - stochastic gradient descent
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
22
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
23 Users:
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
24 ------
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
25
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
26 - New masters and PhD students in the lab should be able to quickly move into
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
27 'production' mode without having to reinvent the wheel.
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
28
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
29 - Students in the two ML classes, able to play with the library to explore new
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
30 ML variants. This means some APIs (e.g. Experiment level) must be really well
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
31 documented and conceptually simple.
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
32
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
33 - Researchers outside the lab (who might study and experiment with our
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
34 algorithms)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
35
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
36 - Partners outside the lab (e.g. Bell, Ubisoft) with closed-source commercial
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
37 projects.
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
38
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
39 Uses:
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
40 -----
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
41
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
42 R1. reproduce previous work (our own and others')
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
43
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
44 R2. explore MLA variants by swapping components (e.g. optimization algo, dataset,
1096
2bbc294fa5ac requirements: Added a use case
Olivier Delalleau <delallea@iro>
parents: 1093
diff changeset
45 hyper-parameters)
1093
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
46
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
47 R3. analyze experimental results (e.g. plotting training curves, finding best
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
48 models, marginalizing across hyper-parameter choices)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
49
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
50 R4. disseminate (or serve as platform for disseminating) our own published algorithms
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
51
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
52 R5. provide implementations of common MLA components (e.g. classifiers, datasets,
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
53 optimization algorithms, meta-learning algorithms)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
54
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
55 R6. drive large scale parallizable computations (e.g. grid search, bagging,
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
56 random search)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
57
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
58 R7. provide implementations of standard pre-processing algorithms (e.g. PCA,
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
59 stemming, Mel-scale spectrograms, GIST features, etc.)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
60
1096
2bbc294fa5ac requirements: Added a use case
Olivier Delalleau <delallea@iro>
parents: 1093
diff changeset
61 R8. provide high performance suitable for large-scale experiments
1093
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
62
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
63 R9. be able to use the most efficient algorithms in special case combinations of
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
64 learning algorithm components (e.g. when there is a fast k-fold validation
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
65 algorithm for a particular model family, the library should not require users
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
66 to rewrite their standard k-fold validation script to use it)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
67
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
68 R10. support experiments on a variety of datasets (e.g. movies, images, text,
1096
2bbc294fa5ac requirements: Added a use case
Olivier Delalleau <delallea@iro>
parents: 1093
diff changeset
69 sound, reinforcement learning?)
1093
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
70
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
71 R11. support efficient computations on datasets larger than RAM and GPU memory
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
72
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
73 R12. support infinite datasets (i.e. generated on the fly)
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
74
1098
4eda3f52ebef v2planning - revs to requirements, added architecture
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1096
diff changeset
75 R13. apply trained models "in production".
4eda3f52ebef v2planning - revs to requirements, added architecture
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1096
diff changeset
76 - e.g. say you try many combinations of preprocessing, models and associated
4eda3f52ebef v2planning - revs to requirements, added architecture
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1096
diff changeset
77 hyper-parameters, and want to easily be able to recover the full "processing
4eda3f52ebef v2planning - revs to requirements, added architecture
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1096
diff changeset
78 pipeline" that performs best, and use it on real/test data later.
1093
a65598681620 v2planning - initial commit of use_cases, requirements
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
79