next up previous
Next: 2.2 Biological Neural Networks Up: 2. Artificial Neural Networks Previous: 2. Artificial Neural Networks

2.1 Background

The motivation of studies in neural networks lies in the flexibility and power of information processing that conventional computing machines do not have. The history of neural networks comes from attempts of modeling a system whose performance is analogous to the most basic functions of human brains. Although most computers can process faster and more precisely than human brains, people have ability to obtain experience then make more sensible decisions [Zur92]. Similar to the fact that the human brain generalizes the rules, the neural network system can ``learn by examples and experience" and perform variety of nonlinear functions that are difficult to describe mathematically [Tay96].

Artificial neural networks are a narrow-sensed abstraction of the human brain, thus the organization of the artificial neural system is very similar to the one of biological neurons. The comprehensive understanding of biological neurons is not complete; however, the basic functionality that contributes to the learning ability of a system is implemented in artificial neural networks. The fundamental element, an artificial neuron, is a model based on known behavior of biological neurons that exhibit most of the characteristics of human brains that we are interested in [Vel98]. This is the most significant difference from conventional computers, which have internal fixed instructions to perform specific functions.

Artificial neural networks can be also described as highly parallel distributed computing models. The fundamental processing units, neurons, are highly connected with strengths, which are dynamically changed during the system's learning process.

The discussion in following sections approach the engineer's perspective of understanding the artificial neural networks. Though artificial neural networks are not an exact copy of biological human brain, it is important to begin with understanding fundamental concepts of biological neurons and the human brain.


next up previous
Next: 2.2 Biological Neural Networks Up: 2. Artificial Neural Networks Previous: 2. Artificial Neural Networks
Kiyoshi Kawaguchi
2000-06-17