Types of artificial neural networks

There are many types of artificial neural networks (ANN).
<a href="/facts/Artificial_neural_network/6V1jMlkx">Artificial neural networks</a> are <a href="/facts/Computational_model/dq1CR6us">computational models</a> inspired by <a href="/facts/Biological_neural_network/pgngqMLf">biological neural networks</a>, and are used to <a href="/facts/Universal_approximation_theorem/IhjwWXa2">approximate</a> <a href="/facts/Function_(mathematics)/CdReEKCh">functions</a> that are generally unknown. Particularly, they are inspired by the behaviour of <a href="/facts/Neuron/G7CyTVdH">neurons</a> and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research. Most artificial neural networks bear only some resemblance to their more complex biological counterparts, but are very effective at their intended tasks (e.g. classification or segmentation).
Some artificial neural networks are <a href="/facts/Adaptive_system/H5oMdF0h">adaptive systems</a> and are used for example to <a href="/facts/Population_model/D0yfI3LX">model populations</a> and environments, which constantly change.
Neural networks can be hardware- (neurons are represented by physical components) or <a href="/facts/Neural_network_software/S0p1pq0v">software-based</a> (computer models), and can use a variety of topologies and learning algorithms.

Types of artificial neural networks open-in-new

Types of artificial neural networks