Supervised Learning

Supervised Learning Learning algorithms which were considered for a single perceptron, linear adaline, and multilayer perceptron belong to the class of supervised learning algorithms. In this case the training data is divided into input signals, Ü´Òµ, and target signals, ´Òµ. A typical learning algorithm is driven by error signals´Òµ which are the differences between the actual network output, Ý´Òµ, and the desire (or target) output for a given input. For a pattern learning, we can express weight update in the following general form ¡Û´Òµ Ä´Û´Òµ Ü´Òµ´Òµµ where Ä represents a learning algorithm. If we say that a neural network can describe a model of data, then a multilayer perceptron describes the data in a form of a hypersurface which approximates a functional relationship between Ü´Òµ, and´Òµ.