MultiLayer Perceptron, MultiLayer Perceptron 
MultiLayer Perceptron, MultiLayer Perceptron 
nd00jan 
Aug 16, 2006, 07:34 AM
Post
#1

Newbie Group: Basic Member Posts: 1 Joined: Aug 16, 2006 Member No.: 5504 
I'm new to Perceptrons and things like that.
For instance on this page: http://diwww.epfl.ch/mantra/tutorial/engli...html/index.html ...at the end there is a question like: "How often does the network find a solution?". When do we know it's find a solution? What's indicates that a solution is found? Can't really get a grip on this... 
lucid_dream 
Aug 16, 2006, 07:56 AM
Post
#2

God Group: Admin Posts: 1711 Joined: Jan 20, 2004 Member No.: 956 
Single layer perceptrons are only capable of learning linearly separable patterns. However, feedforward neural networks with three or more layers (i.e, multilayer perceptrons) have far greater processing power.
The universal approximation theorem for neural networks states that every continuous function that maps intervals of real numbers to some output interval of real numbers can be approximated arbitrarily closely by a multilayer perceptron with just one hidden layer. Multilayer networks use a variety of learning techniques, the most popular being backpropagation. Here the output values are compared with the correct answer to compute the value of some predefined errorfunction. By various techniques the error is then fed back through the network. Using this information, the algorithm adjusts the weights of each connection in order to reduce the value of the error function by some small amount. After repeating this process for a sufficiently large number of training cycles the network will usually converge to some state where the error of the calculations is small. In this case one says that the network has learned a certain target function. To adjust weights properly one applies a general method for nonlinear optimization task that is called gradient descent. For this, the derivative of the error function with respect to the network weights is calculated and the weights are then changed such that the error decreases (thus going downhill on the surface of the error function). For this reason backpropagation can only be applied on networks with differentiable activation functions. Learn more here 
LoFi Version  Time is now: 19th November 2017  12:32 AM 