14-08-2012, 10:30 AM
Multi-Layer Perceptron (MLP)
Multi-Layer Perceptron (MLP).ppt (Size: 475 KB / Downloads: 145)
Today we will introduce the MLP and the backpropagation algorithm which is used to train it
MLP used to describe any general feedforward (no recurrent connections) network
However, we will concentrate on nets with units arranged in layers
Properties of architecture
No connections within a layer
No direct connections between input and output layers
Fully connected between layers
Often more than 3 layers
Number of output units need not equal number of input units
Number of hidden units per layer can be more or less than
input or output units
Credit assignment problem
Problem of assigning ‘credit’ or ‘blame’ to individual elements
involved in forming overall response of a learning system
(hidden units)
In neural networks, problem relates to deciding which weights
should be altered, by how much and in which direction.
Analogous to deciding how much a weight in the early layer contributes to the output and thus the error
We therefore want to find out how weight wij affects the error ie we want: