A class library written in Objective-C++ for building models of connectionist networks . The class-hierarchy is designed to be maximally general and expandable, but also to support specific types of network.
In cognitive psychology, the major formal language for the description of sub-symbolic learning.
An approach to studying intelligence based on storing problem-solving knowledge as a pattern of connections among a very large number of simple processing units operating in parallel. Connectionism is often contrasted with the manipulation of the large symbolic structures traditionally used to represent knowledge in artificial intelligence. It was inspired by the structure of synapses (connections) and neurons (processing units) in the human brain.
The study of the theory and application of neural networks. See: Neural network.
Approach to cognitive science that models thinking by artificial neural networks.
In practice, the study of the theory and application of artificial neural networks. More generally, it's an approach that emphasizes the connections among concepts, rather than their symbolic meaning.
Connectionism is an approach in the fields of artificial intelligence, cognitive science, neuroscience, psychology and philosophy of mind. Connectionism models mental or behavioral phenomena as the emergent processes of interconnected networks of simple units. There are many different forms of connectionism, but the most common forms utilize neural network models.