Professional Documents
Culture Documents
Introduction To Neural Networks: John Paxton Montana State University Summer 2003
Introduction To Neural Networks: John Paxton Montana State University Summer 2003
Networks
John Paxton
Montana State University
Summer 2003
Chapter 6: Backpropagation
1986 Rumelhart, Hinton, Williams
Gradient descent method that minimizes
the total squared error of the output.
Applicable to multilayer, feedforward,
supervised neural networks.
Revitalizes interest in neural networks!
Backpropagation
Appropriate for any domain where inputs
must be mapped onto outputs.
1 hidden layer is sufficient to learn any
continuous mapping to any arbitrary
accuracy!
Memorization versus generalization
tradeoff.
Architecture
input layer, hidden layer, output layer
1 1
y1
x1 z1
ym
xn zp
wpm
vnp
General Process
Feedforward the input signals.
Bipolar Sigmoid
f(x) = -1 + 2 / [1 + e-x]
f(x) = 0.5 * [1 + f(x)] * [1 f(x) ]
Training Algorithm
1. initialize weights to small random
values, for example [-0.5 .. 0.5]
D vij(t+1) = similar
m is [0.0 .. 1.0]