Connection Science · 1991 · 76 citations · 24 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningNatural Language ProcessingDeep LearningDistributed Memory ParallelismLanguage ModelingLanguage ModelsMachine TranslationNatural Language UnderstandingCompositional ModelingNeural Language ModelsTransformational Learning
A number of connectionist models capable of representing data with compositional structure have recently appeared. These new models suggest the intriguing possibility of performing holistic structure-sensitive computations with distributed representations. Two possible forms of holistic inference, transformational inference and confluent inference, are identified and compared. Transformational inference was successfully demonstrated by Chalmers; however, the pure transformational approach does not consider the eventual inference tasks during the process of learning its representations. Confluent inference is introduced as a method for achieving a tight coupling between the distributed representations of a problem and the solution for the given inference task while the net is still learning its representations. A dual-ported RAAM architecture based on Pollack's Recursive Auto-Associative Memory is implemented and demonstrated in the domain of Natural Language translation.
24
Jeffrey L. Elman · Cognitive Science · 1990 · 10.8K citations
Edward H. Madden, Nelson Goodman, Andrew G. van Melsen · Philosophy and Phenomenological Research · 1955 · 4.4K citations
Connectionism and cognitive architecture: A critical analysis
Jerry A. Fodor, Zenon W. Pylyshyn · Cognition · 1988 · 4K citations
Recursive distributed representations
Jordan Pollack · Artificial Intelligence · 1990 · 873 citations