Abu-Mostafa, Y. S. (1993) An algorithm for learning from hints. In: Proceedings of 1993 International Joint Conference on Neural Networks. Vol.2. IEEE , Piscataway, NJ, pp. 1653-1656. ISBN 0-7803-1422-0 http://resolver.caltech.edu/CaltechAUTHORS:ABUijcnn93
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:ABUijcnn93
To take advantage of prior knowledge (hints) about the function one wants to learn, we introduce a method that generalizes learning from examples to learning from hints. A canonical representation of hints is defined and illustrated. All hints are represented to the learning process by examples, and examples of the function are treated on equal footing with the rest of the hints. During learning, examples from different hints are selected for processing according to a given schedule. We present two types of schedules; fixed schedules that specify the relative emphasis of each hint, and adaptive schedules that are based on how well each hint has been learned so far. Our learning method is compatible with any descent technique.
|Item Type:||Book Section|
|Additional Information:||© Copyright 1993 IEEE. Reprinted with permission. This work was supported by the United States AFOSR under Grant No. F49620-92-J-0398.|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Archive Administrator|
|Deposited On:||05 Jan 2007|
|Last Modified:||26 Dec 2012 09:27|
Repository Staff Only: item control page