A Common Framework for Distributed Representation Schemes for Compositional Structure

Over the last few years a number of schemes for encoding compositional structure in distributed representations have been proposed, e.g., Smolensky's tensor products, Pollack's RAAMs, Plate's HRRs, Halford et al's STAR model, and Kanerva's binary spatter codes. All of these schemes can placed in a general framework involving su-perposition and binding of patterns. Viewed in this way, it is often simple to decide whether what can be achieved within one scheme will be able to be achieved in another. Furthermore, placing these schemes in a general framework reveals unexplored regions in which other related representation schemes with interesting properties.

[1]  H. C. LONGUET-HIGGINS,et al.  Non-Holographic Associative Memory , 1969, Nature.

[2]  Janet Metcalfe,et al.  A composite holographic associative recall model , 1982 .

[3]  B. Murdock A Theory for the Storage and Retrieval of Item and Associative Information. , 1982 .

[4]  Bennet B. Murdock,et al.  A distributed memory model for serial-order information. , 1983 .

[5]  J. Eich Levels of processing, encoding specificity, elaboration, and CHARM. , 1985, Psychological review.

[6]  Jerome A. Feldman,et al.  Neural Representation of Conceptual Knowledge. , 1986 .

[7]  C. P. Dolan,et al.  Tensor manipulation networks: connectionist and symbolic approaches to comprehension, learning, and planning , 1989 .

[8]  Charles P. Dolan,et al.  Tensor Product Production System: a Modular Architecture and Representation , 1989 .

[9]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[10]  Jordan B. Pollack,et al.  Recursive Distributed Representations , 1990, Artif. Intell..

[11]  David J. Chalmers,et al.  Syntactic Transformations on Distributed Representations , 1990 .

[12]  E. HintonGeoffrey Mapping part-whole hierarchies into connectionist networks , 1990 .

[13]  David S. Touretzky,et al.  BoltzCONS: Dynamic Symbol Structures in a Connectionist Network , 1990, Artif. Intell..

[14]  Geoffrey E. Hinton Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1991 .

[15]  Paul Smolensky,et al.  Distributed Recursive Structure Processing , 1990, SCAI.

[16]  Tony Plate,et al.  Holographic Reduced Representations: Convolution Algebra for Compositional Distributed Representations , 1991, IJCAI.

[17]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[18]  Arthur B. Markman,et al.  Analogy-- Watershed or Waterloo? Structural alignment and the development of connectionist models of analogy , 1992, NIPS 1992.

[19]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[20]  B B Murdock,et al.  TODAM2: a model for the storage and retrieval of item, associative, and serial-order information. , 1993, Psychological review.

[21]  Alessandro Sperduti,et al.  Encoding Labeled Graphs by Labeling RAAM , 1993, NIPS.

[22]  T. E. Lange,et al.  Below the Surface: Analogical Similarity and Retrieval Competition in Reminding , 1994, Cognitive Psychology.

[23]  Geoffrey E. Hinton,et al.  Distributed representations and nested compositional structure , 1994 .

[24]  A. Sperduti Labeling Raam , 1994 .

[25]  Pentti Kanerva,et al.  Binary Spatter-Coding of Ordered K-Tuples , 1996, ICANN.

[26]  Alessandro Sperduti,et al.  Supervised neural networks for the classification of structures , 1997, IEEE Trans. Neural Networks.

[27]  T. Plate,et al.  Structure Matching And Transformation With Distributed Representations , 1997 .

[28]  Alessandro Sperduti,et al.  Distributed representations for terms in hybrid reasoning systems , 1997 .

[29]  Lars Niklasson,et al.  Can Connectionist Models Exhibit Non-Classical Structure Sensitivity? , 2019, Proceedings of the Sixteenth Annual Conference of the Cognitive Science Society.