Aritificial Neural Network in detail

Elements of ANN,its type & application areas.

Processing Elements of Artificial Neural Network

A processing unit is made up of summing unit followed by an output unit. The function of a summing unit is to take n input values, weight each input value and calculate the weighted sum of those values.

Based on the sign of the weight of each input, it is determined whether the input has a positive weight or a negative weight.

The weighted sum of the summing unit is known as Activation Value and based on the signal from this activation value, the output is produced.

Both the input and output can be either continuous or discrete as well as they can be either deterministic or fuzzy.

Positive weight also termed as excitatory input.

Negative weight also termed as inhibitory input.

Two important areas where ANNs have a huge potential of applications are in Speech Recognition  and Image Processing

Applications in Speech Recognition

1.Vowel Classification

2.Recognition of vowel-consonant segments

3.Recognition of stop consonant-vowel utterances in Indian languages

4.Nettalk

5.Phonetic Typewriter

Applications in Image Processing

1.Recognition of Symbols (used in Olympics)

2.Recognition of handwriting

3.Segmentation of image

4.Classification and segmentation of texture