Package pylearn :: Package examples :: Module linear_classifier
[hide private]

Module linear_classifier

source code

T. Bertin-Mahieux (2008) University of Montreal bertinmt@iro.umontreal.ca

linear_classifier.py Simple script that creates a linear_classifier, and learns the parameters using backpropagation.

This is to illustrate how to use theano/pylearn. Anyone who knows how to make this script simpler/clearer is welcome to make the modifications.

Classes [hide private]
modelgraph
class that contains the graph of the model
model
The model! Contains needed matrices, needed functions, and a link to the model graph.
Functions [hide private]
 
cost_function(*args, **kwargs)
default cost function, quadratic
source code
 
die_with_usage()
help menu
source code

Imports: os, sys, time, copy, pickle, numpy, N, NR, cost, theano, T