Wolfram Library Archive

Courseware Demos MathSource Technical Notes
All Collections Articles Books Conference Proceedings

Neural Network Simulations using Mathematica

S. Duncan
R. Tweney
Journal / Anthology

Submitted for the 26th Annual Meeting of the Society for Computers in Psychology
Year: 1996

Several neural networks were developed in the Mathematica programming environment in order to test the results of Kim and Myung (1995), which claimed that the addition of temporal summation to a neural network facilitated a semantic priming effect. We replicated their results, removed temporal summation then found the same priming effect. With these simulations, Mathematica was shown to be a powerful environment for neural network development, exhibiting distinct advantages over other environments in terms of programming ease, flexibility of data structures and the assessment of network performance.

*Applied Mathematics > Computer Science