David Rumelhart
In plain wordsAn American psychologist who, with Geoffrey Hinton and Ronald Williams, showed in 1986 how to train multilayer neural networks, launching the modern revival of the field.
American cognitive psychologist at the University of California, San Diego, and from 1987 Stanford University. With James McClelland he led the PDP Research Group, whose two-volume 'Parallel Distributed ProcessingParallel Distributed Processing, prop. n.: A two-volume 1986 book by a group of psychologists and computer scientists that revived interest in brain-like neural networks and made the training method behind modern AI widely known.' (1986) made connectionismconnectionism, n.: The view that minds and intelligent machines are best built from huge networks of simple, neuron-like units whose connection strengths are learned, rather than from explicit rules and symbols. a major program in cognitive science, modeling perception, memory and language with networks of simple units. With Geoffrey HintonGeoffrey Hinton, prop. n.: A British-Canadian scientist whose decades of persistent work on brain-inspired neural networks laid the foundations of modern AI; often called a 'godfather of AI', he now warns publicly about its dangers. and Ronald Williams he published 'Learning representations by back-propagating errors' (Nature, 1986), which showed that backpropagationbackpropagation, n.: The method neural networks use to learn from mistakes: it works backward from the error to figure out how much each internal connection contributed, so every connection can be adjusted in the right direction. could train the hidden layershidden layer, n.: Any layer of a neural network between the input and the output. Its values are never shown to the user; they are the network's internal working-out. of multilayer networksmultilayer perceptron, n.: A neural network made of several layers of artificial neurons, each connected to every neuron in the next layer. It is the simplest kind of deep network and a component of almost every modern model. to discover useful internal representations; though the method had earlier origins, this paper made it the standard way to train neural networksneural network, n.: A kind of computer program that learns a task from examples by tuning thousands to billions of connections between simple number-crunching units, an arrangement loosely inspired by nerve cells in the brain.. Earlier he worked on schemas and story understanding and, with McClelland, on the interactive activation model of word recognition (1981). A MacArthur Fellow (1987), he is commemorated by the Rumelhart Prize in cognitive science.
Related
- backpropagationbackpropagation, n.: The method neural networks use to learn from mistakes: it works backward from the error to figure out how much each internal connection contributed, so every connection can be adjusted in the right direction.
- Parallel Distributed ProcessingParallel Distributed Processing, prop. n.: A two-volume 1986 book by a group of psychologists and computer scientists that revived interest in brain-like neural networks and made the training method behind modern AI widely known.
- connectionismconnectionism, n.: The view that minds and intelligent machines are best built from huge networks of simple, neuron-like units whose connection strengths are learned, rather than from explicit rules and symbols.
- multilayer perceptronmultilayer perceptron, n.: A neural network made of several layers of artificial neurons, each connected to every neuron in the next layer. It is the simplest kind of deep network and a component of almost every modern model.
- Geoffrey HintonGeoffrey Hinton, prop. n.: A British-Canadian scientist whose decades of persistent work on brain-inspired neural networks laid the foundations of modern AI; often called a 'godfather of AI', he now warns publicly about its dangers.
- representation learningrepresentation learning, n.: Letting a computer work out for itself how best to describe its data, such as the edges and shapes in images or the meanings of words, instead of relying on descriptions people design by hand.
Sources
- Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature 323: 533–536.
- Rumelhart, D. E., McClelland, J. L. & the PDP Research Group (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press.
Mentioned in
Geoffrey HintonGeoffrey Hinton, prop. n.: A British-Canadian scientist whose decades of persistent work on brain-inspired neural networks laid the foundations of modern AI; often called a 'godfather of AI', he now warns publicly about its dangers., Michael I. JordanMichael I. Jordan, prop. n.: An American computer scientist and statistician who did much to bring probability and statistics into machine learning, and who trained many of the field's leaders., Parallel Distributed ProcessingParallel Distributed Processing, prop. n.: A two-volume 1986 book by a group of psychologists and computer scientists that revived interest in brain-like neural networks and made the training method behind modern AI widely known., Paul WerbosPaul Werbos, prop. n.: An American scientist whose 1974 doctoral thesis set out backpropagation, the method of passing errors backward that now trains nearly all neural networks., Seppo LinnainmaaSeppo Linnainmaa, prop. n.: A Finnish computer scientist who in 1970 first published the method for computing all of a program's derivatives in one backward pass, the mathematical core of backpropagation.