Neural Network

When it comes to information technology, a neural network is a system of programs and data structures that approximates the operation of the human brain. A neural network usually involves a large number of processors operating in parallel, each with its own small sphere of knowledge and access to data in its local memory. It works the same way as the biological nervous system works. This type of system learns by example. It is configured for a specific application to do things like recognize patterns of classify data. It can be thought of as an expert in the category of information that it is given, and much easier answer what if questions.

Typically, a neural network is initially trained or fed large amounts of data and rules about data relationships. Neural Networks can extract patterns and detect trends that are too complex for humans to notice. For example, "A grandfather is older than a person's father". A program can then tell the network how to behave in response to an external stimulus's. For example, to input from a computer user who is interacting with the network, or can initiate activity on its own within the limits of its access to the external world. 

In making determinations, neural networks use several principles including gradient-based training, fuzzy logic, genetic algorithms, and Bayesian methods. Neural networks are sometimes described in terms of knowledge layers. With more complex networks having deeper layers. In feed forward systems, learned relationships about data can "feed forward" to higher layers of knowledge. Neural networks can also learn temporal concepts and have been widely used in signal processing and time series analysis.

There are advantages and disadvantages to using neural networks. There is no "perfect" machine learning method. For every problem, for which a certain method is good, there is another problem for which the same method will fail. The methods at which it fails may be solved by other methods quite easily however. Neural networks are quite simple to implement. Although, neural networks cannot be retrained. If you add data later, this is almost impossible to add to an existing network. Also, neural networks often exhibit patterns similar to those exhibited by humans. However this is more of interest in cognitive sciences than for practical examples.

Current applications of neural networks include: oil exploration data analysis, weather prediction, the interpretation of nucleotide sequences in biology labs, and the exploration of models of thinking and consciousness. What makes neural networks more valuable than traditional computing process is their ability to learn. Neural networks offer a different way to analyze data, and to recognize patterns within that data, than traditional computing methods. However, they are not a solution for all computing problems. Traditional computing methods work well for problems that can be well characterized. Balancing checkbooks, keeping ledgers, and keeping tabs of inventory are well defined and do not require the special characteristics of neural networks.