Neural NetworksA neural network also known as an artificial neural network provides a unique computing architecture whose potential has only just begun to be exploited. They are used to address problems that are intractable or cumbersome with traditional methods. These new computing architectures are radically different from the computers widely used today. ANNs are massively parallel systems that rely on dense arrangements of interconnects and surprisingly simple processors (Cr95, Ga93). Artificial neural networks are named after the networks of nerve cells in the brain. Although a large amount of biological detail is eliminated in these computational models, ANNs retain enough of the structure observed in the brain to provide insights into how biological neural processing may work (He90). Neural networks provide an effective approach for a wide spectrum of applications. Neural networks excel at problems involving patterns, which include pattern mapping, pattern completion, and pattern classification (He95). Neural networks can be applied to translate images into keywords or even translate financial data into financial forecasts (Wo96). Neural networks use a parallel processing structure that has a large number of processors and many interconnections between them. These processors are much simpler than typical central processing units (He90). In a neural network, each processor is connected to many of its neighbors so that there are many more interconnections than processors. The power of the neural network lies in the enormous number of interconnections (Za93). ANNs are generating a lot of interest among engineers and scientists. Artificial neural network models contribute to our understanding of biological models. They also provide a new type of parallel processing that has powerful capabilities and potential for creative hardware implementations, meets the demand for fast computing hardware, and offers the potential to solve application problems (Wo96). Neural networks stimulate our imagination and incessant desire to understand the self and, furthermore, equip us with a unique set of technological tools. But what has sparked the most interest in ne...... middle of paper...... "When computers imitate how the brain works," Boston Business Journal, vol. 14 (June 10, 1994), pp 24.[Vo94] Vogel, William, "Minimally Connective, Auto-Associative, NeuralNetworks," Connection Science, vol. 6 (1 January 1994), pp 461.[Wo96] Information on the Internet. http://www.mindspring.com/~zsol/nnintro.html http://ourworld.compuserve.com/homepages/ITechnologies/ http://sharp.bu.edu/inns/nn.html http://www .eeb.ele.tue.nl/neural/contents/neural_networks.html http://www.ai.univie.ac.at/oefai/nn/ http://www.nd.com/welcome/whatisnn.htm http ://www.mindspring.com/~edge/neural.html http://vita.mines.colorado.edu:3857/lpratt/applied-nnets.html[Za93] Zahedi, F. Intelligent Systems for Business: Systems experts with NeuralNetworks, Wadsworth Publishing Company, California, 1993..