Including Hints in Training Neural Nets
- 1 September 1991
- journal article
- Published by MIT Press in Neural Computation
- Vol. 3 (3) , 418-427
- https://doi.org/10.1162/neco.1991.3.3.418
Abstract
The aim of a neural net is to partition the data space into near optimal decision regions. Learning such a partitioning solely from examples has proven to be a very hard problem (Blum and Rivest 1988; Judd 1988). To remedy this, we use the idea of supplying hints to the network—as discussed by Abu-Mostafa (1990). Hints reduce the solution space, and as a consequence speed up the learning process. The minimum Hamming distance between the patterns serves as the hint. Next, it is shown how to learn such a hint and how to incorporate it into the learning algorithm. Modifications in the net structure and its operation are suggested, which allow for a better generalization. The sensitivity to errors in such a hint is studied through some simulations.Keywords
This publication has 2 references indexed in Scilit:
- Learning from hints in neural networksJournal of Complexity, 1990
- On the complexity of loading shallow neural networksJournal of Complexity, 1988