| |
1960s - 1970s: Expert Systems Gain Attendance |
 |
The concept of  expert systems dates back to the 1960s but first gained prominence in the 1970s. Conclusive for this development were the insights of the Stanford University professor Edward Feigenbaum, who in 1977 demonstrated that the problem-solving capacity of a computer program rather is a result of the knowledge it posses, than of the applied programming techniques and formalisms.
Expert systems were designed to mimic the knowledge and reasoning capabilities of a human specialist in a given domain by using (top down) artificial intelligence techniques. Made possible by the large storage capacity of the computers at the time, expert systems had the potential to interpret statistics and formulate rules. An initial use of expert systems was to diagnose and treat human physical disorders, but as its applications in the market place were extensive over the course of the following years they were also employed in fields such as stock market forecast, taxation, chemistry, and geology.
|
|
Neural network
A bottom-up artificial intelligence approach, a neural network is a network of many very simple processors ("units" or "neurons"), each possibly having a (small amount of) local memory. The units are connected by unidirectional communication channels ("connections"), which carry numeric data. The units operate only on their local data and on the inputs they receive via the connections. A neural network is a processing device, either an algorithm, or actual hardware, whose design was inspired by the design and functioning of animal brains and components thereof. Most neural networks have some sort of "training" rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, neural networks "learn" from examples and exhibit some structural capability for generalization.
|
|
|
