A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming.

Descriptor ID	D016571
MeSH Number(s)	G17.485 L01.224.065.605 L01.725.500
Concept/Terms	Neural Networks (Computer) Neural Networks (Computer) Network, Neural (Computer) Networks, Neural (Computer) Neural Network (Computer) Models, Neural Network Model, Neural Network Network Model, Neural Network Models, Neural Neural Network Model Perceptrons Perceptron Connectionist Models Connectionist Model Model, Connectionist Models, Connectionist Neural Network Models

Below are MeSH descriptors whose meaning is more general than "Neural Networks (Computer)".

Below are MeSH descriptors whose meaning is related to "Neural Networks (Computer)".

Below are MeSH descriptors whose meaning is more specific than "Neural Networks (Computer)".