Neural Networks differ from Expert Systems
Businesses around the world utilize different kinds of systems in order to help them direct their company and gain competitive advantage over their competition. These businesses use two different kind of systems to help them which are expert systems and neural networks. Both of these systems help solve problems but they work in entirely different ways.
The first characteristic that differs between them is the way that they process information. Expert systems use sequential processing by going through the data one line or rule at a time. It basically goes through the process logically using rule concepts to guide it to its answer. It is best used for questions that involve calculations such as balancing checkbooks and inventory management. Artificial neural networks process their data in a parallel environment. This means that it can do more than one thing at a time while trying to come up with the best solution. It can also process information such as images and pictures which expert systems can not process.
Another characteristic in which they differ is how they learn in order to have the knowledge to solve problems. Expert systems learn by being fed rules didactically. The system uses this knowledge base in order to know what path it should take when certain questions are answered the way that they are. They also learn from accounting, word processing, math inventory and digital communication application. Neural networks learn by example and interpretation. Some of the ways that they learn include sensor processing, speech recognition, pattern recognition and text recognition.
Source: Joe Bartunek
You might also like:
Stock market analysts on trial2002-02-09 14:24:25 by on-trial
The amount of poor and self-interested advice that is being issued by brokerages and their analysts. To this day, the majority of stockbrokers are compensated on the number of trades their customers make, not on the returns they generate for them or on the quality of the advice they provide. We believe that the price targets and analyst ratings are made with several masters in mind, none of whom are the individual investor. In a similar fashion, sell-side stock analysts are generally compensated based upon the overall profitability of their firms, not the quality or accuracy of their analysis. In the end, analysts have minimal structural incentive to be accurate in their predictions; rather their built-in incentive is to be as favorable to their corporate clients as possible. It is a...
Gurus' Results Stay Consistently Bad — Forbes
Investment gurus make their money selling market predictions, not following them. Their overall performance has been historically and consistently dismal. Why people pay for market predictions is a one of Wall Street's biggest mysteries.
Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part III (Lecture Notes ... Computer Science and General Issues)