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

Neural Computation

September 1995, Vol. 7, No. 5, Pages 1021-1039
(doi: 10.1162/neco.1995.7.5.1021)
© 1995 Massachusetts Institute of Technology
Precision and Approximate Flatness in Artificial Neural Networks
Article PDF (1.03 MB)
Abstract

Several of the major classes of artificial neural networks' output functions are linear combinations of elements of approximately flat sets. This gives a tool for understanding the precision problem as well as providing a rationale for mixing types of networks. Approximate flatness also helps explain the power of artificial neural network techniques relative to series regressions—series regressions take linear combinations of flat sets, while neural networks take linear combinations of the much larger class of approximately flat sets.