Wolfram Library Archive

Courseware Demos MathSource Technical Notes
All Collections Articles Books Conference Proceedings

Mathematica: A Flexible Design Environment for Neural Networks

S. Duncan
R. Tweney
Journal / Anthology

Behavior Research Methods, Instruments & Computers
Year: 1997
Volume: 29
Issue: 2
Page range: 194-199

Several neural networks were developed in Mathematica in order to explore the role of “spiky” neurons in neural network memory simulations. Using Mathematica 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.

*Applied Mathematics > Computer Science