A Method for Learning from Hints
- Creators
- Abu-Mostafa, Yaser S.
Abstract
We address the problem of learning an unknown function by putting together several pieces of information (hints) that we know about the function. We introduce a method that generalizes learning from examples to learning from hints. A canonical representation of hints is defined and illustrated for new types of hints. All the 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 that we may choose to use.
Additional Information
© 1993 Morgan Kaufmann. The author would like to thank Ms. Zehra Kok for her valuable input. This work was supported by the AFOSR under grant number F49620-92-J-0398.Attached Files
Published - 616-a-method-for-learning-from-hints.pdf
Files
Name | Size | Download all |
---|---|---|
md5:e1dbfc64948ba09abb9ade15f50b37c9
|
1.8 MB | Preview Download |
Additional details
- Eprint ID
- 64070
- Resolver ID
- CaltechAUTHORS:20160128-163222557
- F49620-92-J-0398
- Air Force Office of Scientific Research (AFOSR)
- Created
-
2016-01-29Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field
- Series Name
- Advances in Neural Information Processing Systems
- Series Volume or Issue Number
- 5