neural network or neural computing, computer architecture modeled upon the human brain's interconnected system of neurons. Neural networks imitate the brain's ability to sort out patterns and learn from trial and error, discerning and extracting the relationships that underlie the data with which it is presented. Most neural networks are software simulations run on conventional computers. In neural computers, transistor circuits serve as the neurons and variable resistors act as the interconnection between axons and dendrites (see nervous system). A neural network on an integrated circuit, with 1,024 silicon "neurons," has also been developed. Each neuron in the network has one or more inputs and produces an output; each input has a weighting factor, which modifies the value entering the neuron. The neuron mathematically manipulates the inputs, and outputs the result. The neural network is simply neurons joined together, with the output from one neuron becoming input to others until the final output is reached. The network learns when examples (with known results) are presented to it; the weighting factors are adjusted—either through human intervention or by a programmed algorithm—to bring the final output closer to the known result.

Neural networks are good at providing very fast, very close approximations of the correct answer. Although they are not as well suited as conventional computers for performing mathematical calculations or moving and comparing alphabetic characters, neural networks excel at recognizing shapes or patterns, learning from experience, or sorting relevant data from irrelevant. Their applications can be categorized into classification, recognition and identification, assessment, monitoring and control, and forecasting and prediction. Among the tasks for which they are well suited are handwriting recognition, foreign language translation, process control, financial forecasting, medical data interpretation, artificial intelligence research, and parallel processing implementations of conventional processing tasks. In an ironic reversal, neural networks are being used to model disorders of the brain in an effort to discover better therapeutic strategies.

network, in computing, two or more computers connected for the purpose of routing, managing, and storing rapidly changing data. A local area network (LAN), which is restricted by distances of up to one mile, and a metropolitan area network (MAN), which is restricted to distances of up to 60 miles, connect personal computers and workstations (each called a node) over dedicated, private communications links. A wide area network (WAN) connects large numbers of nodes over long-distance communications links, such as common carrier telephone lines, over distances ranging from that between major metropolitan centers to that between continents. An internet is a connection between networks. The Internet is a WAN that connects thousands of disparate networks in the U.S., Canada, Europe, Asia, and elsewhere, providing global communication between nodes on government, educational, and industrial networks. Networks allow for resource sharing (e.g., multiple computers sharing one printer), data sharing, and communication or data exchange (e.g., electronic mail).

metropolitan area network (MAN): see local area network.

local area network (LAN), a computer network dedicated to sharing data among several single-user workstations or personal computers, each of which is called a node. A LAN can have from two to several hundred such nodes, each separated by distances of several feet to as much as a mile, and should be distinguished from connections among computers over public carriers, such as telephone circuits, that are used for other purposes. Because of the relatively small areas involved, the nodes in a LAN can be connected by special high-data-rate cables. A metropolitan area network (MAN) is defined as being restricted to a larger area (maximum distances of 50-60 miles) than a LAN but one still small enough so that dedicated links (such as microwave links) can be used. See also modem.

Type of parallel computation in which computing elements are modeled on the network of neurons that constitute animal nervous systems. This model, intended to simulate the way the brain processes information, enables the computer to “learn” to a certain degree. A neural network typically consists of a number of interconnected processors, or nodes. Each handles a designated sphere of knowledge, and has several inputs and one output to the network. Based on the inputs it gets, a node can “learn” about the relationships between sets of data, sometimes using the principles of fuzzy logic. For example, a backgammon program can store and grade results from moves in a game; in the next game, it can play a move based on its stored result and can regrade the stored result if the move is unsuccessful. Neural networks have been used in pattern recognition, speech analysis, oil exploration, weather prediction, and the modeling of thinking and consciousness.

Learn more about neural network with a free trial on Britannica.com.

Two or more computers and peripheral equipment (e.g., printers) that are connected with one another for the purpose of exchanging data electronically. Two basic network types are local area networks (LANs) and wide-area networks. Wide-area networks connect computers and smaller networks to larger networks over greater geographical areas, including different continents. Communications may occur over cables, fibre optics, or satellites, but most computer users access the network with a modem, using telephone lines. The largest wide-area network is the Internet. In the 1990s the World Wide Web was introduced and became the most popular way to access other Internet sites.

Learn more about network, computer with a free trial on Britannica.com.