2002 · 27 citations · 7 references
Artificial IntelligenceEngineeringMachine LearningNeural Networks (Machine Learning)Neural NetworkLearning AlgorithmLearning ControlRecurrent Neural NetworkSocial SciencesFeedback ConnectionsAutoregressive Backpropagation AlgorithmNonlinear Time SeriesSequence ModellingComputational Learning TheoryComputer EngineeringInverse ProblemsNeural Networks (Computational Neuroscience)Computer ScienceDeep Neural Networks
Describes an extension to error backpropagation that allows the nodes in a neural network to encode state information in an autoregressive 'memory'. This neural model gives such networks the ability to learn to recognize sequences and context-sensitive patterns. Building upon the work of A. Wieland (1990) concerning nodes with a single feedback connection, the authors generalize the method to n feedback connections and address stability issues. The learning algorithm is derived, and a few applications are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
7
Backpropagation through time: what it does and how to do it
Paul J. Werbos · Proceedings of the IEEE · 1990 · 4.8K citations
Learning and Sequential Decision Making
Andrew G. Barto, Richard S. Sutton, Chris Watkins · 1989 · 353 citations
Learning to Tell Two Spirals Apart
Kevin Lang · 1988 · 288 citations · Full text