An Overview of Strategies for Neurosymbolic Integration

At the crossroads of symbolic and neural processing, researchers have been actively investigating the synergies that might be obtained from combining the strengths of these two paradigms. Neurosymbolic integration comes in two avors: unifed and hybrid. Uniied approaches strive to attain full symbol-processing functionalities using neural techniques alone while hybrid approaches blend symbolic reasoning and rep-resentational models with neural networks. This papers attempts to clarify and compare the objectives, mechanisms, variants and underlying assumptions of these major integration approaches.

[1]  Vasant Honavar,et al.  Symbolic Artificial Intelligence and Numeric Artificial Neural Networks: Towards A Resolution of the Dichotomy , 1995 .

[2]  Rolf Pfeifer,et al.  An Approach to Integrating Expert Systems with Connectionist Networks , 1990, AI Commun..

[3]  P. Magrez,et al.  A symbolic interpretation for back‐propagation networks , 1992, Int. J. Intell. Syst..

[4]  L.-M. Fu,et al.  Integration of neural heuristics into knowledge-based inference , 1989, International 1989 Joint Conference on Neural Networks.

[5]  Rama Chellappa,et al.  Combined Neural Network and Rule-Based Framework for Probabilistic Pattern Recognition and Discovery , 1991, NIPS.

[6]  R. Sun.  On Variable Binding in Connectionist Networks , 1992 .

[7]  T. Samad.  Hybrid distributed/local connectionist architectures , 1989, International 1989 Joint Conference on Neural Networks.

[8]  Li-Chen Fu,et al.  Mapping rule-based systems into neural architecture , 1990, Knowl. Based Syst..

[9]  Yoichi Hayashi,et al.  A Neural Expert System with Automated Extraction of Fuzzy If-Then Rules , 1990, NIPS.

[10]  Kanaan A. Faisal,et al.  Symbolic parsing via subsymbolic rules , 1992 .

[11]  J. Fodor,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.

[12]  G. Edelman,et al.  Real brains and artificial intelligence , 1989 .

[13]  Wolfgang Ertel,et al.  Automatic Acquisition of Search Guiding Heuristics , 1990, CADE.

[14]  William G. Wee,et al.  An intelligent hybrid system for wastewater treatment , 1992 .

[15]  Dean A. Pomerleau,et al.  Combining artificial neural networks and symbolic processing for autonomous robot guidance , 1991 .

[16]  Lokendra Shastri,et al.  A Connectionist Approach to Knowledge Representation and Limited Inference , 1988, Cogn. Sci..

[17]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[18]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[19]  Lawrence J. Henschen,et al.  What Is Automated Theorem Proving? , 1985, J. Autom. Reason..

[20]  Stephen I. Gallant,et al.  Neural network learning and expert systems , 1993 .

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

[22]  Stephen H. Lane,et al.  Integrating Knowledge-Based System and Neural Network Techniques for Robotic Skill Acquisition , 1989, IJCAI.

[23]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[24]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[25]  N. S. Park,et al.  A localist network architecture for logical inference based on temporal synchrony approach to dynamic variable binding , 1995 .

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

[27]  Susan I. Hruska,et al.  Hybrid systems: the equivalence of rule-based expert system and artificial neural network inference , 1991 .

[28]  Geoffrey E. Hinton,et al.  A Distributed Connectionist Production System , 1988, Cogn. Sci..

[29]  Lokendra Shastri,et al.  Rules and Variables in Neural Nets , 1991, Neural Computation.

[30]  Lawrence A. Bookman.  A Microfeature-based Scheme for Modelling Semantics , 1987, IJCAI.

[31]  Stephen H. Lane,et al.  Robotic Skill Acquisition Based on Biological Principles , 1992 .

[32]  R. Nakano,et al.  Medical diagnostic expert system based on PDP model , 1988, IEEE 1988 International Conference on Neural Networks.

[33]  Stephen I. Gallant,et al.  Connectionist expert systems , 1988, CACM.

[34]  Padhraic Smyth,et al.  An Information Theoretic Approach to Rule-Based Connectionist Expert Systems , 1988, NIPS.

[35]  J. Jeffrey Mahoney and Raymond J. Mooney,et al.  Modifying Network Architectures For Certainty-Factor Rule-Base Revision , 1994 .

[36]  Larry R. Medsker,et al.  Hybrid Neural Network and Expert Systems , 1994, Springer US.

[37]  Rolf Pfeifer,et al.  Cooperative Hybrid Systems , 1991, IJCAI.

[38]  S. Pinker,et al.  On language and connectionism: Analysis of a parallel distributed processing model of language acquisition , 1988, Cognition.

[39]  Arnaud Giacometti.  Modèles hybrides de l'expertise , 1992 .

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

[41]  Franz Kurfess,et al.  Chcl -a Connectionist Inference System , 1991 .

[42]  Geoffrey G. Towell,et al.  Symbolic knowledge and neural networks: insertion, refinement and extraction , 1992 .

[43]  Susan I. Hruska,et al.  Back-propagation learning in expert networks , 1992, IEEE Trans. Neural Networks.

[44]  Richard Fozzard,et al.  A Connectionist Expert System that Actually Works , 1988, NIPS.

[45]  M. Gasser,et al.  A connectionist model of sentence genera-tion in a first and second language , 1988 .

[46]  C. Lee Giles,et al.  Extraction, Insertion and Refinement of Symbolic Rules in Dynamically Driven Recurrent Neural Networks , 1993 .

[47]  G. F. Tremblay,et al.  Bright Air, Brilliant Fire: On the Matter of the Mind, Gerald M. Edelman. 1992. Basic Books, New York, NY. 280 pages. ISBN: 0-465-05245-2. $25.00 , 1992 .

[48]  B. Bachmann.  The design of neural networks using a priori knowledge , 1995 .

[49]  Andreas Stolcke,et al.  Tree matching with recursive distributed representations , 1992, AAAI Conference on Artificial Intelligence.

[50]  Andrew Sohn,et al.  Connectionist Production Systems in Local and Hierarchical Representation , 1991 .

[51]  Volker Tresp,et al.  Network Structuring and Training Using Rule-Based Knowledge , 1992, NIPS.

[52]  Ron Sun,et al.  Integrating Rules and Connectionism for Robust Reasoning , 1990, Dagstuhl Seminar on Parallelization in Inference Systems.