These neurons may be physically constructed or simulated by a digital computer. Each neuron takes many input signals, then, based on an internal weighting system, produces a single output signal that's typically sent as input to another neuron.
How they learn: Artificial neural networks typically start out with randomized weights for all their neurons. This means that they don't "know" anything and must be trained to solve the particular problem for which they are intended. .
Broadly speaking, there are two methods for training an ANN, depending on the problem it must solve.
A self-organizing ANN (often called a Kohonen after its inventor) is exposed to large amounts of data and tends to discover patterns and relationships in that data. Researchers often use this type to analyze experimental data.
A back-propagation ANN, conversely, is trained by humans to perform specific tasks. During the training period, the teacher evaluates whether the ANN's output is correct. If it's correct, the neural weightings that produced that output are reinforced; if the output is incorrect, those weightings responsible are diminished. .
This type is most often used for cognitive research and for problem-solving applications.
Concluding with Economic uses: Large financial institutions have used ANN's to improve performance in such areas as bond rating, credit scoring, target marketing and evaluating loan applications. These systems are typically only a few percentage points more accurate than their predecessors, but because of the amounts of money involved, they are very profitable. ANN's are now used to analyze credit card transactions to detect likely instances of fraud.
With all that the computer is learning now a new question arises: How long before a computer can learn to understand and execute the attributes of a good sense of humor? It is believed that the theory of AI has existed long before recorded, but was not made conceivable until the invention of the electronic computer in 1941 (Dreyfus p.
