A Caltech Library Service

Generalizing smoothness constraints from discrete samples

Ji, Chuanyi and Snapp, Robert R. and Psaltis, Demetri (1990) Generalizing smoothness constraints from discrete samples. Neural Computation, 2 (2). pp. 188-197. ISSN 0899-7667. doi:10.1162/neco.1990.2.2.188.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Article
Related URLs:
URLURL TypeDescription
Additional Information:© 1990 Massachusetts Institute of Technology. Received 15 August 1989; accepted 20 February 1990. Posted Online March 13, 2008. We would like to thank our colleagues, Mr. Mark Neifeld, Dr. Jeff Yu, Dr. Fai Mok, and Mr. Alan Yamamura for helpful discussions. This work was supported by the JPL Director’s Discretionary Fund and in part by DARPA and the Air Force Office of Scientific Research.
Funding AgencyGrant Number
JPL Director’s Discretionary FundUNSPECIFIED
Defense Advanced Research Projects AgencyUNSPECIFIED
Air Force Office of Scientific ResearchUNSPECIFIED
Issue or Number:2
Record Number:CaltechAUTHORS:JICnc90
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:13648
Deposited By: Tony Diaz
Deposited On:17 Jun 2009 21:33
Last Modified:08 Nov 2021 22:39

Repository Staff Only: item control page