Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

May 15, 1996, Vol. 8, No. 4, Pages 805-818.
(doi: 10.1162/neco.1996.8.4.805)
© 1996 Massachusetts Institute of Technology
Analog versus Discrete Neural Networks
Article PDF (665.47 KB)
Abstract

We show that neural networks with three-times continuously differentiable activation functions are capable of computing a certain family of n-bit Boolean functions with two gates, whereas networks composed of binary threshold functions require at least Ω(log n) gates. Thus, for a large class of activation functions, analog neural networks can be more powerful than discrete neural networks, even when computing Boolean functions.