Artificial Neural Network

Artificial neural networks (ANNs) or connectionist systems are a computational model used in machine learning, computer science and other research disciplines, which is based on a large collection of connected simple units called artificial neurons, loosely analogous to axons in a biological brain. Connections between neurons carry a unidirectional signal with an activating strength that is proportional to the strength of the connection between those neurons.^{[further explanation needed]} If the combined incoming signals are strong enough, the "postsynaptic" neuron becomes activated and a signal propagates to downstream neurons connected to it. Such systems can be trained from examples, rather than explicitly programmed, and excel in areas where the solution or feature detection is difficult to express in a traditional computer program. Like other machine learning methods, neural networks have been used to solve a wide variety of tasks, like computer vision and speech recognition, that are difficult to solve using ordinary rule-based programming.

Typically, neurons are connected in layers, and signals travel from the first (input), to the last (output) layer. Modern neural network projects typically have a few thousand to a few million neural units and millions of connections; their computing power is similar to a worm brain, several orders of magnitude simpler than a human brain. The signals and state of artificial neurons are real numbers, typically between 0 and 1. There may be a threshold function or limiting function on each connection and on the unit itself, such that the signal must surpass the limit before propagating. Back propagation is the use of forward stimulation to modify connection weights, and is sometimes done to train the network using known correct outputs.^{[further explanation needed]} However, the success is unpredictable: after training, some systems are good at solving problems while others are not. Training typically requires several thousand cycles of interaction.^{[citation needed]}

The goal of the neural network is to solve problems in the same way that a human would, although several neural network categories are more abstract. New brain research often stimulates new patterns in neural networks. One new approach is use of connections which span further to connect processing layers rather than adjacent neurons. Other research being explored with the different types of signal over time that axons propagate, such as deep learning, interpolates greater complexity than a set of boolean variables being simply on or off. Newer types of network are more free flowing in terms of stimulation and inhibition, with connections interacting in more chaotic and complex ways. ^{[clarification needed]} Dynamic neural networks are the most advanced, in that they dynamically can, based on rules, form new connections and even new neural units while disabling others.^{[citation needed]}

Historically, the use of neural network models marked a directional shift in the late 1980s from high-level (symbolic) artificial intelligence, characterized by expert systems with knowledge embodied in if-then rules, to low-level (sub-symbolic) machine learning, characterized by knowledge embodied in the parameters of a cognitive model with some dynamical system.