Attractor Networks

Artificial neural networks (ANNs), sometimes referred to as connectionist networks, are computational models based loosely on the neural architecture of the brain. Over the past twenty years, ANNs have proven to be a fruitful framework for modeling many aspects of cognition, including perception, attention, learning and memory, language, and executive control. A particular type of ANN, called an attractor network, is central to computational theories of consciousness, because attractor networks can be analyzed in terms of properties—such as temporal stability, and strength, quality, and discreteness of representation— that have been ascribed to conscious states. Some theories have gone so far as to posit that attractor nets are the computational substrate from which conscious states arise.