16-10-2010, 09:50 AM
Artificial Neural Networks.doc (Size: 49 KB / Downloads: 311)
Artificial Neural Networks
INTRODUCTION
During the infancy of the development of Neural Networks technology, one thing that excited people’s interest was its analogy to biological systems. Even though not all has been understood about the learning processes of human neural systems, Artificial Neural Networks (ANN) have, without a doubt, provide the solution to problems in different application areas [1]. The brain is a highly complex, nonlinear and parallel information processing system. It consists of about one hundred billion neural cells, each connected to about 10,000 neighboring neurons and receiving signals from there. The brain routinely accomplishes perceptual recognition tasks (e.g., recognizing a familiar face in a scene) in about 100-200 msec. The neuron, the basic information processing element (PE) in the central nervous system plays a very important and diverse role in human sensory processing, control and cognition. The brain is able to do complex tasks by its ability to learn from experience. An Artificial Neural network is designed to model the working of human brain.
The ANN is usually implemented using electronic components (digital & analog) and/or simulated on a digital computer. It employs massive interconnection of simple computing cells called “neurons” or “processing elements (PE)” It resembles the brain in two ways:
• Knowledge is acquired by the network through learning process,
• Inter neuron connection strength (synaptic weights) are responsible for storing the knowledge.
The way the synaptic weights change is what makes the design of ANNs. Such an approach is close to linear adaptive filter theory, which is well established and is used in many diverse fields such as communication, control, sonar, radar, and biomedical engineering.