Mercurial > pylearn
comparison sandbox/simple_autoassociator/main.py @ 393:36baeb7125a4
Made sandbox directory
author | Joseph Turian <turian@gmail.com> |
---|---|
date | Tue, 08 Jul 2008 18:46:26 -0400 |
parents | simple_autoassociator/main.py@e2cb8d489908 |
children | 8849eba55520 |
comparison
equal
deleted
inserted
replaced
392:e2cb8d489908 | 393:36baeb7125a4 |
---|---|
1 #!/usr/bin/python | |
2 """ | |
3 A simple autoassociator. | |
4 | |
5 The learned model is:: | |
6 h = sigmoid(dot(x, w1) + b1) | |
7 y = sigmoid(dot(h, w2) + b2) | |
8 | |
9 Binary xent loss. | |
10 | |
11 LIMITATIONS: | |
12 - Only does pure stochastic gradient (batchsize = 1). | |
13 """ | |
14 | |
15 | |
16 import numpy | |
17 | |
18 nonzero_instances = [] | |
19 nonzero_instances.append({0: 1, 1: 1}) | |
20 nonzero_instances.append({0: 1, 2: 1}) | |
21 | |
22 #nonzero_instances.append({1: 0.1, 5: 0.5, 9: 1}) | |
23 #nonzero_instances.append({2: 0.3, 5: 0.5, 8: 0.8}) | |
24 ##nonzero_instances.append({1: 0.2, 2: 0.3, 5: 0.5}) | |
25 | |
26 import model | |
27 model = model.Model() | |
28 | |
29 for i in xrange(100000): | |
30 # Select an instance | |
31 instance = nonzero_instances[i % len(nonzero_instances)] | |
32 | |
33 # SGD update over instance | |
34 model.update(instance) |