Artificial Neural Networks : Architecture and Learning Process

Architectural Overview of neural networks

Based on architecture, neural networks are basically of two types:

1. Feed-forward networks

Feed-forward ANNs (fig 2) allow only unidirectional signal transmission, i.e., from input to output, without any feedback loop. Also called as bottom-up or top-down.

Application: Pattern Recognition

2. Feedback networks

Feedback networks (fig 3) allow signals to travel in both directions by introducing loops. These networks are very powerful, get extremely complicated and dynamic because of their continuous change of state before coming to equilibrium.

Brief Explanation of the Learning Process

The neural networks recognize patterns and respond subsequently in following two ways.

1. Associative mapping refers to the process of learning to produce a particular pattern on the set of input units.

2. Regularity detection in which units learn to respond to particular properties of the input patterns.

The relationships among patterns are stored in case of Associative learning, whereas, in regularity detection the response of each unit has a particular ‘meaning’.

Behavior of an Artificial Neural Network: Its Transfer Function

The transfer function typically falls into one of three categories:

· linear (or ramp) (output proportional to total weighted input)

· threshold (input compared with a predetermined threshold value and the output is decided accordingly)

· sigmoid (output varying continuously, but not linearly with input changes)