Connectionism

connectionistparallel distributed processingconnectionist modelsconnectionist networkscomputational modelsconnectionist approachconnectionistsnetwork approach and connectionist approachparallelparallel distributed algorithm development
Connectionism is an approach in the fields of cognitive science that hopes to explain mental phenomena using artificial neural networks (ANN).wikipedia
193 Related Articles

Cognitive science

cognitive scientistcognitive sciencescognitive
Connectionism is an approach in the fields of cognitive science that hopes to explain mental phenomena using artificial neural networks (ANN).
The former view uses connectionism to study the mind, whereas the latter emphasizes symbolic computations.

Mind

mentalhuman mindmental content
Connectionism is an approach in the fields of cognitive science that hopes to explain mental phenomena using artificial neural networks (ANN).
Theoretical approaches to explain how mind emerges from the brain include connectionism, computationalism and Bayesian brain.

Deep learning

deep neural networkdeep neural networksdeep-learning
The success of deep learning networks in the past decade has greatly increased the popularity of this approach, but the complexity and scale of such networks has brought with them increased interpretability problems.
Artificial neural networks (ANNs) or connectionist systems are computing systems inspired by the biological neural networks that constitute animal brains.

David Rumelhart

RumelhartDavid E. RumelhartD.E. Rumelhart
A lot of the research that led to the development of PDP was done in the 1970s, but PDP became popular in the 1980s with the release of the books Parallel Distributed Processing: Explorations in the Microstructure of Cognition - Volume 1 (foundations) and Volume 2 (Psychological and Biological Models), by James L. McClelland, David E. Rumelhart and the PDP Research Group.
David Everett Rumelhart (June 12, 1942 – March 13, 2011) was an American psychologist who made many contributions to the formal analysis of human cognition, working primarily within the frameworks of mathematical psychology, symbolic artificial intelligence, and parallel distributed processing.

James McClelland (psychologist)

James McClellandJay McClellandMcClelland
A lot of the research that led to the development of PDP was done in the 1970s, but PDP became popular in the 1980s with the release of the books Parallel Distributed Processing: Explorations in the Microstructure of Cognition - Volume 1 (foundations) and Volume 2 (Psychological and Biological Models), by James L. McClelland, David E. Rumelhart and the PDP Research Group.
He is best known for his work on statistical learning and Parallel Distributed Processing, applying connectionist models (or neural networks) to explain cognitive phenomena such as spoken word recognition and visual word recognition.

Paul Smolensky

Smolensky, Paul
Many researchers, such as the connectionist Paul Smolensky, have argued that connectionist models will evolve toward fully continuous, high-dimensional, non-linear, dynamic systems approaches.
Smolensky is the recipient of the 2005 Rumelhart Prize for his pursuit of the ICS Architecture, a model of cognition that aims to unify Connectionism and symbolism, where the symbolic representations and operations are manifested as abstractions on the underlying connectionist networks.

Edward Thorndike

Edward L. ThorndikeEdward Lee ThorndikeE. L. Thorndike
But by the early 20th century, Edward Thorndike was experimenting on learning that posited a connectionist type network.
His work on comparative psychology and the learning process led to the theory of connectionism and helped lay the scientific foundation for educational psychology.

Cognitive psychology

cognitive psychologistcognitivecognitive psychologists
Spreading activation is always a feature of neural network models, and it is very common in connectionist models used by cognitive psychologists.

Steven Pinker

Pinker, StevenPinkerNancy Etcoff
As connectionism became increasingly popular in the late 1980s, some researchers (including Jerry Fodor, Steven Pinker and others) reacted against it.
In particular, his work with Alan Prince published in 1989 critiqued the connectionist model of how children acquire the past tense of English verbs, arguing instead that children use default rules such as adding "-ed" to make regular forms, sometimes in error, but are obliged to learn irregular forms one by one.

Psychology

psychologicalpsychologistpsychologists
Many connectionist principles can be traced to early work in psychology, such as that of William James.
In the United States, Edward Lee Thorndike initiated "connectionism" studies by trapping animals in "puzzle boxes" and rewarding them for escaping.

Language of thought hypothesis

language of thoughtMentaleselanguage of thought" hypothesis
Some researchers argued that the trend in connectionism represented a reversion toward associationism and the abandonment of the idea of a language of thought, something they saw as mistaken.
It relies on a version of functionalist materialism, which holds that mental representations are actualized and modified by the individual holding the propositional attitude, and it challenges eliminative materialism and connectionism.

Catastrophic interference

catastrophic forgettingsequential learning
Neural networks are an important part of the network approach and connectionist approach to cognitive science.

Machine learning

machine-learninglearningstatistical learning
This line, too, was continued outside the AI/CS field, as "connectionism", by researchers from other disciplines including Hopfield, Rumelhart and Hinton.

Syntax

syntacticsyntacticalsyntactically
One common implementation of such an approach makes use of a neural network or connectionism.

Domain specificity

domain-specificdomain specificdomain-specificity
Prominent examples of such domain-general views include Jean Piaget’s theory of cognitive development, and the views of many modern connectionists.

Pandemonium architecture

Although not perfect, the pandemonium architecture influenced the development of modern connectionist, artificial intelligence, and word recognition models.

Artificial neuron

artificial neuronsMcCulloch–Pitts neuronneurons
Many earlier researchers advocated connectionist style models, for example in the 1940s and 1950s, Warren McCulloch and Walter Pitts (MP neuron), Donald Olding Hebb, and Karl Lashley.

Jerry Fodor

FodorFodor, JerryFodorian
As connectionism became increasingly popular in the late 1980s, some researchers (including Jerry Fodor, Steven Pinker and others) reacted against it.
Fodor draws on the work of Noam Chomsky to both model his theory of the mind and to refute alternative architectures such as connectionism.

Philosophy of mind

mindmental philosophyphilosophy of the mind
The recent popularity of dynamical systems in philosophy of mind have added a new perspective on the debate; some authors now argue that any split between connectionism and computationalism is more conclusively characterized as a split between computationalism and dynamical systems.
Eliminativists such as Patricia and Paul Churchland argue that while folk psychology treats cognition as fundamentally sentence-like, the non-linguistic vector/matrix model of neural network theory or connectionism will prove to be a much more accurate account of how the brain works.

Artificial intelligence

AIA.I.artificially intelligent
Interest in neural networks and "connectionism" was revived by David Rumelhart and others in the middle of the 1980s.

Computational theory of mind

computationalismComputational theories of mindcomputationalist
They argued that connectionism, as then developing, threatened to obliterate what they saw as the progress being made in the fields of cognitive science and psychology by the classical approach of computationalism.

Associationism

associationistassociationist psychologyAssociationist school
Some researchers argued that the trend in connectionism represented a reversion toward associationism and the abandonment of the idea of a language of thought, something they saw as mistaken.

Eliminative materialism

eliminativismeliminative materialisteliminative materialists
In recent years, this latter argument has been fortified by the theory of connectionism.

Fault tolerance

fault-tolerantfault tolerantfault-tolerance
Some advantages of the connectionist approach include its applicability to a broad array of functions, structural approximation to biological neurons, low requirements for innate structure, and capacity for graceful degradation.

Explainable artificial intelligence

explainable AIExplainabilityinterpretability problems
The success of deep learning networks in the past decade has greatly increased the popularity of this approach, but the complexity and scale of such networks has brought with them increased interpretability problems.