2000 · 28 citations · 10 references
ComputingComputer ScienceData MiningMachine LearningTime Series AnalysisNeural NetworksNeural RepresentationPattern RecognitionRepresentation LearningUnsupervised LearningDiscrete Approximation SchemesQuantizationRecurrent Neural NetworksSelf-organizing MapsSelf-organizing NetworksTemporal Data AnalysisTemporal Data EncodingVector Quantization
Vector quantization consists in finding a discrete approximation of a continuous input. One of the most popular neural algorithms related to vector quantization is the, so called, Kohonen map. We generalize vector quantization to temporal data, introducing context quantization. We propose a recurrent network inspired by the Kohonen map, the contextual self-organizing map, that develops near-optimal representations of context. We demonstrate quantitatively that this algorithm shows better performance than the other neural methods proposed so far.
10
Jeffrey L. Elman · Cognitive Science · 1990 · 10.8K citations
Jeffrey L. Elman · Cognitive Science · 1990 · 2.9K citations · Full text
Geoffrey J. Chappell, John G. Taylor · Neural Networks · 1993 · 231 citations