Generalizing Smoothness Constraints from Discrete Samples
- 1 June 1990
- journal article
- Published by MIT Press in Neural Computation
- Vol. 2 (2) , 188-197
- https://doi.org/10.1162/neco.1990.2.2.188
Abstract
We study how certain smoothness constraints, for example, piecewise continuity, can be generalized from a discrete set of analog-valued data, by modifying the error backpropagation, learning algorithm. Numerical simulations demonstrate that by imposing two heuristic objectives — (1) reducing the number of hidden units, and (2) minimizing the magnitudes of the weights in the network — during the learning process, one obtains a network with a response function that smoothly interpolates between the training data.Keywords
This publication has 2 references indexed in Scilit:
- What Size Net Gives Valid Generalization?Neural Computation, 1989
- III-Posed problems early vision: from computational theory to analogue networksProceedings of the Royal Society of London. B. Biological Sciences, 1985