Review and Experiments on SDMSCue

Authors: Ashraf Anwar

Abstract:

In this work, I present a review on Sparse Distributed Memory for Small Cues (SDMSCue), a variant of Sparse Distributed Memory (SDM) that is capable of handling small cues. I then conduct and show some cognitive experiments on SDMSCue to test its cognitive soundness compared to SDM. Small cues refer to input cues that are presented to memory for reading associations; but have many missing parts or fields from them. The original SDM failed to handle such a problem. SDMSCue handles and overcomes this pitfall. The main idea in SDMSCue; is the repeated projection of the semantic space on smaller subspaces; that are selected based on the input cue length and pattern. This process allows for Read/Write operations using an input cue that is missing a large portion. SDMSCue is augmented with the use of genetic algorithms for memory allocation and initialization. I claim that SDM functionality is a subset of SDMSCue functionality.

Keywords: Artificial intelligence, recall, recognition, SDM, SDMSCue.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1070657

References:

[1] Anwar, Ashraf, ÔÇÿSparse Distributed Memory with Evolutionary Mechanisms-, Proceedings of Genetic and Evolutionary Computation Conference Workshop (GECCO), 1999, pp. 339-40.
[2] Anwar, Ashraf, Dasgupta, Dipankar, and Franklin, Stan, Using Genetic Algorithms for Sparse Distributed Memory Initialization, Proceedings of Congress on Evolutionary Computation (CEC), 1999.
[3] Anwar, Ashraf, and Franklin, Stan, Sparse Distributed Memory for "Conscious" Software Agents, Cognitive Systems Research Journal, UK: Elsevier, December 2003, v 4 n 4, pp. 339-54.
[4] Anwar, Ashraf, and Franklin, Stan, A Sparse Distributed Memory Capable of Handling Small Cues, SDMSCue, IFIP International Federation for Information Processing, USA: Springer Science+Business Media Inc., Formerly Kluwer Boston Inc, 2005, vol. 172, pp. 23, ISSN: 1571-5736 (Paper) 1861-2288 (Online).
[5] Doyle, John, A Model for Deliberation, Action, and Introspection (AI TR), USA: MIT, AI Lab, 1980.
[6] Evans, Richard, and Surkan, Alvin, Relating Number of Processing Elements in a Sparse Distributed Memory Model to Learning Rate and Generalization, APL Quote Quad, Aug 1991, v 21, n 4, pp. 166.
[7] Feldman, Robert S., Understanding Psychology, USA: McGraw Hill, 2005.
[8] Franklin, Stan, Artificial Minds, USA: MIT Press, 1995.
[9] Franklin, Stan, Autonomous Agents as Embodied AI, Cybernetics and Systems Journal, special issue on Epistemological Issues in Embedded AI, 1997.
[10] Franklin, Stan, and Graesser, Art, A Software Agent Model of Consciousness, Consciousness and Cognition Journal, 1999, v 8, pp. 285-305.
[11] Franklin, Stan, Kelemen, Arpad, and McCauley, Lee, IDA: A Cognitive Agent Architecture, IEEE Transactions on Systems, Man, and Cybernetics, USA: IEEE, NJ, 1998.
[12] Glenberg, Arthur M., What Memory is for?, Behavioral and Brain Sciences Journal, USA: Cambridge University Press, 1997.
[13] Hely, T., The Sparse Distributed Memory: A Neurobiologically Plausible Memory Model?, Master's Thesis, UK: Edinburgh University, Department of Artificial Intelligence, 1994.
[14] Ingrand, F. F., and Georgeff, M. P., Managing Deliberation and Reasoning in Real-Time AI Systems, Proceedings of the Workshop on Innovative Approaches to Planning, Scheduling and Control, pp. 284-91, 1990.
[15] Kanerva, Pentti, and Raugh, Michael, Sparse Distributed Memory, RIACS, Annual Report, USA: NASA Ames Research Center, Moffett Field, CA, 1987.
[16] Kanerva, Pentti, Sparse Distributed Memory, USA: MIT Press, 1988.
[17] Kanerva, Pentti, The Organization of an Autonomous Learning System, USA: RIACS-TR-88, NASA Ames Research Center, Moffett Field, CA, 1988.
[18] Kanji, Gopal K., 100 Statistical Tests, USA: Sage Publications, 1999.
[19] Loftus, Geoffrey, and Loftus, Elizabeth, Human Memory, the Processing of Information, USA: Lawrence Erlbaum Associates, 1976.
[20] Rao, Rajesh P. N., and Fuentes, Olac, Learning Navigational Behaviors using a Predictive Sparse Distributed Memory, Proceedings of the 4th international Conference on Simulation of Adaptive Behavior, From Animals to Animats IV, 1996, pp. 382.
[21] Rao, Rajesh P. N., and Fuentes, Olac, Hierarchical Learning of Navigation Behaviors in an Autonomous Robot using a Predictive Sparse Distributed Memory, Machine Learning Journal, April 1998, v 31, n 1/3, pp. 87-113.
[22] Scott, E., Fuller, C., and O'Brien, W., Sparse Distributed Associative Memory for the Identification of Aerospace Acoustic Sources, AIAA Journal, September 1993, v 31, n 9, pp. 1583.
[23] Vogt, W. Paul, Dictionary of Statistics and Methodology, 2nd Edition, USA: Sage Publications, 1998.