Abstract
Several neural networks were developed inMathematica in order to explore the role of “spiky” neurons in neural network memory simulations. UsingMathematica for this task confirmed its value as a powerful tool for neural network development: It exhibited distinct advantages over other environments in programming ease, flexibility of data structures, and the graphical assessment of network performance.
Article PDF
Similar content being viewed by others
References
Duncan, S.,Kurz, E.,Rivardo, M., &Strasser, R. (1996, November).Semantic priming in a simple two-layer neural network. Poster presented at 37th Annual Meeting of the Psychonomic Society, Chicago.
Freeman, J. A. (1994).Simulating neural networks with Mathematica. New York: Addison-Wesley.
Gronlund, S. D., Sheu, C.-F., &Ratcliff, R. (1990). Implementation of global memory models with software that does symbolic computation.Behavior Research Methods, Instruments, & Computers,22, 228–235.
Hinton, G. E., McClelland, J. L., &Rumelhart, D. E. (1986). Distributed representations. In D. E. Rumelhart & J. L. McClelland (Eds.),Parallel distributed processing: Explorations in the microstructure of cognition. Vol. 1: Foundations (pp. 77–109). Cambridge, MA: MIT Press.
Kim, C. &Myung, I. J. (1995). Incorporating real-time random time effects in neural networks: A temporal summation mechanism. In J. D. Moore & J. F. Lehman (Eds.),Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society (pp. 472–477). Hillsdale, NJ: Erlbaum.
Lorig, T. S., &Urbach, T. P. (1995). Event-related potential analysis usingMathematica.Behavior Research Methods, Instruments, & Computers,27, 358–366.
Masters, T. (1993).Practical neural network recipes in C++. San Diego: Academic Press.
Ratcliff, R. (1994). Using computers in empirical and theoretical work in cognitive psychology.Behavior Research Methods, Instruments, & Computers,26, 94–106.
Rumelhart, D. E., McClelland, J. L. (Eds.) (1986).Parallel distributed processing: Explorations in the microstructure of cognition. Vol. 1: Foundations. Cambridge, MA: MIT Press.
Wolfram, S. (1994).Mathematica (Version 2.2.2) [Computer programming language]. Champaign, IL: Wolfram Research, Inc.
Wolfram, S. (1996).Mathematica (Version 3) [Computer programming language]. Cambridge: Cambridge University Press.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Acknowledgment is made to In Jae Myung and Cheongtag Kim for graciously sharing their neural network code and their advice in helping the authors to understand the principles underlying “spiky” neural nets. The authors also thank Elke M. Kurz, Mark Rivardo, and Rose Strasser for their criticisms and suggestions.
Rights and permissions
About this article
Cite this article
Duncan, S.C., Tweney, R.D. Mathematica: A flexible design environment for neural networks. Behavior Research Methods, Instruments, & Computers 29, 194–199 (1997). https://doi.org/10.3758/BF03204810
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.3758/BF03204810