Objectives 4 Perceptron Learning Rule

← Back to document page

Objectives4-1 4 4 Perceptron Learning Rule Objectives4-1Theory and Examples4-2Learning Rules4-2Perceptron Architecture4-3Single-Neuron Perceptron4-5Multiple-Neuron Perceptron4-8Perceptron Learning Rule4-8Test Problem4-9Constructing Learning Rules4-10Unified Learning Rule4-12Training Multiple-Neuron Perceptrons4-13Proof of Convergence4-15Notation4-15Proof4-16Limi tations4-18Summary of Results4-20Solved Problems4-21Epilogue4-33Further Reading4-34Exercises4-36 Objectives One of the questions we raised in Chapter 3 was: How do we determine the weight matrix and bias for Perceptron networks with many inputs, where it is impossible to visualize the decision boundaries? In this chapter we will describe an algorithm for training Perceptron networks, so that they can learn to solve classification problems.

contribution was the introduction of a learning rule for training perceptron networks to solve pattern recognition problems [Rose58]. ... terns into a finite number of classes. This is especially useful in such appli- ... th element of the network output vector as pa 1 AA n AA W AA b R x 1 S x R S x 1 S x 1 S x 1 Input RSAA AA AA a = hardlim

  Introduction, Elements, Finite