(Enter summary)
Abstract: Consider the problem of learning input/output mappings through
exploration, e.g. learning the kinematics or dynamics of a robotic
manipulator. If actions are expensive and computation is cheap,
then we should explore by selecting a trajectory through the input
space which gives us the most amount of information in the
fewest number of steps. I discuss how results from the field of optimal
experiment design may be used to guide such exploration, and
demonstrate its use on a simple kinematics... (Update)
Cited by: More
How to Use the Minimal Separators of a Graph for Its Chordal .. - Parra, Scheffler (1994)
(Correct)
Active Learning for Multi-Class Logistic Regression - Keywords Active Learning
(Correct)
Active Learning for Logistic Regression - Schein (2004)
(Correct)
Similar documents (at the sentence level):
14.4%: Neural Network Exploration Using Optimal Experiment Design - Cohn (1994)
(Correct)
Active bibliography (related documents): More All
0.5: The Development and Comparison of Robust Methods for.. - Torr, Murray (1997)
(Correct)
0.2: Shall We Use a Dynamic Model to Control the Motions of.. - Fr'ed'eric Plumet.. (1995)
(Correct)
0.2: An Experimental Procedure for Autonomous Joint Sensor.. - Astley, Hayward
(Correct)
Similar documents based on text: More All
0.0: The ATM Forum Technical Committee - Physical Layer High (1995)
(Correct)
0.0: A Dark Matter Hypothesis for the Cowan Effect -- A Peak at.. - Decay Events Theodore
(Correct)
0.0: A Guidance Scheme for Automated Tetrahedal Truss Structure.. - Doggett (1996)
(Correct)
Related documents from co-citation: More All
41: Information-based objective functions for active data selection
- MacKay
32: Theory of Optimal Experiments (context) - Fedorov - 1972
19: Active learning in multilayer perceptrons
- Fukumizu - 1996
BibTeX entry: (Update)
Cohn, DA (1994). Neural network exploration using optimal experiment design. In JD Cowan, G Tesauro & J Allspector, editors, Advances in Neural Information Processing Systems, 6. San Mateo, CA: Morgan Kaufmann, 679-686. http://citeseer.ist.psu.edu/da94neural.html More
@inproceedings{ cohn94neural,
author = "David A. Cohn",
title = "Neural Network Exploration Using Optimal Experiment Design",
booktitle = "Advances in Neural Information Processing Systems",
volume = "6",
publisher = "Morgan Kaufmann Publishers, Inc.",
editor = "Jack D. Cowan and Gerald Tesauro and Joshua Alspector",
pages = "679--686",
year = "1994",
url = "citeseer.ist.psu.edu/da94neural.html" }
Citations (may not include all citations):
128
Theory of Optimal Experiments (context) - Fedorov - 1972
114
The parti-game algorithm for variable resolution reinforceme..
- Moore - 1994
107
Forward models: Supervised learning with a distal teacher
- Jordan, Rumelhart - 1992
96
Information-based objective functions for active data select..
- MacKay - 1992
73
Supervised learning from incomplete data via an EM approach
- Ghahramani, Jordan - 1994
48
Active Exploration in Dynamic Environments
- Thrun, Moller - 1992
44
Selecting concise training sets from clean data (context) - Plutowski, White - 1993
37
Training connectionist networks with queries and selective s.. (context) - Cohn, Atlas et al. - 1990
18
Neural model of adaptive hand-eye coordination for single po.. (context) - Kuperstein - 1988
4
On finding exciting trajectories for identification experime.. (context) - Armstrong - 1989
2
Elements of Statistical Computing (context) - Trans, Networks et al. - 1988
1
Constructing hidden units using examples and queries (context) - Robotics, -- et al. - 1991
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.ai.mit.edu/people/cohn/papers.html): More
Separating Formal Bounds from Practical Performance in Learning.. - Cohn (1992)
(Correct)
Minimizing Statistical Bias with Queries - Cohn (1997)
(Correct)
Improving Generalization with Active Learning - Cohn, Atlas, al. (1992)
(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