The Neural Network Approach to Artificial Intelligence
Known as the “bottom-up” approach to the research and development of intelligent machines, the neural network approach seeks to replicate in a computer the actions and functions of biological neurons found in the human body. Given the advances made in this field of study, however, artificial neurons do not necessarily model their biological counterparts.
Neurons are cellular transmitters of information that work by means of the electrical signals that pass through one neuron to another. A neural network is, therefore, a group of neurons that are connected to each other in complex structures. A single neuron is not intelligent; it requires interconnectivity to function efficiently. One of the goals of artificial intelligence is to mimic traits of these biological networks, especially since they are useful in the performance of tasks requiring classification or pattern recognition.
Two issues are largely responsible for hindering full-scale development of artificial neural networks. Firstly, the construction of neuron simulators is cost-prohibitive. Accurately replicating the number of neurons in something even as small as a fly would be expensive. And, putting economic considerations aside, current computers are still thousands of times too small to be on scale with the human brain. Secondly, current computer architecture still needs more pathways between components. Despite these limitations, neural networks have already produced some impressive results. Police Departments, for example, use them to spot corruption.
See also:
The Expert Systems Approach to Artificial Intelligence
Web Resources On The Neural Network Approach to Artificial Intelligence
American Association for Artificial Intelligence
Wikipedia: Artificial Intelligence
Book Resources On The Neural Network Approach to Artificial IntelligenceArtificial Intelligence: A Modern Approach by Stuart J. Russel and Peter Norvig
Comparative Cognitive Robotics: Computation and Human Experience by Agre, Philip E., et al
|
|
|
