Laboratory
Introduction to the
Neural Network Toolbox

Neural networks, originally inspired by their biological namesakes, are composed of many simple intercommunicating elements, or neurons, working in parallel to solve a problem.

What makes them exciting is the fact that once a network has been set up, it can learn in a self-organizing way that seems to mimic simple biological nervous systems. Because neural networks can be trained to respond in parallel to the inputs presented to them, they often are much faster than more conventional methods.

At the MATLAB prompt type help nnet for a list of neural network help topics. Type help nndemos for a list of demonstrations. To run, for example, the simplest perceptron demo type demop1.

[ Summer School home page ] [ Lecture timetable ] [ School Map ]
[ HELP ] [ FAQ ] [ Email the organisers ] [ MATLAB homepage ]
[ Toolboxes page ]

---

Last Update 3 January 1996