Lorien Y. Pratt, Jack Mostow, Candace A. Kamm  Home/Search
Context Related
| ohiostate.edu/pub/...pratt.aaai91.ps.Z Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: egbert.cistron.nl/neuroprose (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: A touted advantage of symbolic representations is the ease of transferring learned information from one intelligent agent to another. This paper investigates an analogous problem: how to use information from one neural network to help a second network learn a related task. Rather than translate such information into symbolic form (in which it may not be readily expressible), we investigate the direct transfer of information encoded as weights. Here, we focus on how transfer can be used to... (Update)
Context of citations to this paper: More
...the form of suggesting an appropriate decomposition of the global task. A modular approach can also reduce training times (Pratt, Mosow and Kamm, 1991) and make subsequent modification and extension easier (Gallinari, 1995) An interesting example of the variety of...
...are often not stressed as highly. Pratt, for example, has given attention to the problem of knowledge transfer among di erent tasks [65, 66, 67]. Here the goal is to apply knowledge acquired in one learning task to another learning task in order to speed learning and possibly...
Cited by: More
Pattern Analysis and Applications manuscript No. - Will Be Inserted (Correct)
Scaling-up RAAMs - Blair (1997) (Correct)
Neural Network Knowledge Extraction - Cristea, Cristea, Okamoto (1997) (Correct)
Active bibliography (related documents): More All
0.3: Improving discriminability based transfer by modifying the IM.. - Pratt, Gough (Correct)
0.3: Refinement of Approximate Domain Theories by.. - Towell, Shavlik.. (1990) (Correct)
0.2: Improving a Phoneme Classification Neural Network through.. - Pratt, Kamm (1991) (Correct)
Similar documents based on text: More All
0.1: Transferring Previously Learned Back-Propagation Neural Networks.. - Pratt (1993) (Correct)
0.0: A Fuzzy-Logic and Multi-Layer Perceptron Hybrid Model.. - Lallement, Alexandre (1998) (Correct)
0.0: Using Background Knowledge to Improve Inductive Learning of DNA.. - Hirsh (1994) (Correct)
Related documents from co-citation: More All
12: Induction of Decision Trees (context) - Quinlan - 1986
11: Programs for machine learning (context) - Quinlan - 1993
10: Learning internal representations - Baxter - 1995
BibTeX entry: (Update)
L. Y. Pratt, J. Mostow, and C. A. Kamm, Direct Transfer of Learned Information Among Neural Networks, in: Proceedings of the Ninth National Conference on Artificial Intelligence, Anaheim, CA (1991), 584--589. http://citeseer.ist.psu.edu/pratt91direct.html More
@inproceedings{ lorien91direct,
author = "Pratt, Lorien Y. and Mostow, Jack and Kamm, Candace A.",
title = "{D}irect {T}ransfer of {L}earned {I}nformation among {N}eural {N}etworks",
booktitle = "Proceedings of the Ninth National Conference on Artificial Intelligence ({AAAI}-91)",
month = "July",
publisher = "AAAI",
pages = "584-589",
year = "1991",
url = "citeseer.ist.psu.edu/pratt91direct.html" }
Citations (may not include all citations):1491 Learning internal representations by error propagation (context) - Rumelhart, Hinton et al. - 1987
122 Predicting the future: A connectionist approach (context) - Andreas, Huberman et al. - 1990
49 Dynamic Error Propagation Networks (context) - Anthony - 1989
34 A neuralnet training program based on conjugate-gradient opt.. (context) - Etienne, Ronald - 1989
9 Parallel Distributed Processing: Explorations in the Microst.. (context) - Rumelhart, McClelland et al. - 1987
8 Improving a phoneme classification neural network through pr.. - Pratt, Kamm - 1991
4 Effect of neural network input span on phoneme classificatio.. (context) - Kamm, Singhal - 1990
3 and Towell (context) - Shavlik, Mooney - 1991
1 Recognition of semantically incorrect rules: A neural-networ.. (context) - Suppl, Fu - 1990
1 An acoustic-phonetic data base (context) - CSE, Oregon et al. - 1987
1 Refinement of approximate domain theories by knowledge-based.. (context) - neural, algorithms et al. - 1990
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.egbert.cistron.nl/neuroprose.html): More
A Widrow-Hoff learning-rule for a generalization of.. - Abdi, Valentin.. (1996) (Correct)
A generalized autoassociator model for face processing.. - Abdi, Valentin, O'Toole (1996) (Correct)
The Cocktail Party Listener - Abolfazlian, Karlsen (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC