Ch' 20 Neural Networks

1
Ch. 20 Neural Networks

• Supplemental slides for CSE 327
• Prof. Jeff Heflin

2
A Neuron
3
Perceptron Learning

• function PERCEPTRON-LEARNING(examples,network)
  returns a perceptron hypothesis
• inputs examples, a set of examples with input x
  and output y network, a perceptron with
  weights Wj and activation function g
• repeat for each e in examples do Err ?
  ye g(in) Wj ? Wj ? ? Err ? g(in) ?
  xje until some stopping criteria is
  satisfied return NEURAL-NET-HYPOTHESIS(network)
• From Figure 20.21, p. 742