Jonathan Baxter

CoRR, 2020

2019

Some observations concerning Off Training Set (OTS) error.

[BibT_eX]

[DOI]

CoRR, 2019

General Matrix-Matrix Multiplication Using SIMD features of the PIII.

[BibT_eX]

[DOI]

CoRR, 2019

Hebbian Synaptic Modifications in Spiking Neurons that Learn.

[BibT_eX]

[DOI]

CoRR, 2019

92c/MFlops/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster.

[BibT_eX]

[DOI]

Robert Edwards

CoRR, 2019

Learning Internal Representations (PhD Thesis).

[BibT_eX]

[DOI]

CoRR, 2019

2009

A tag in the hand: supporting semantic, social, and spatial navigation in museums.

[BibT_eX]

[DOI]

Proceedings of the 27th International Conference on Human Factors in Computing Systems, 2009

Using technologies to support reminiscence.

[BibT_eX]

[DOI]

Proceedings of the 2009 British Computer Society Conference on Human-Computer Interaction, 2009

2008

ArtLinks: fostering social awareness and reflection in museums.

[BibT_eX]

[DOI]

Proceedings of the 2008 Conference on Human Factors in Computing Systems, 2008

2004

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.

[BibT_eX]

[DOI]

Evan Greensmith

J. Mach. Learn. Res., 2004

2002

Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning.

[BibT_eX]

[DOI]

J. Comput. Syst. Sci., 2002

Scalable Internal-State Policy-Gradient Methods for POMDPs.

[BibT_eX]

Proceedings of the Machine Learning, 2002

2001

Experiments with Infinite-Horizon, Policy-Gradient Estimation.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2001

Infinite-Horizon Policy-Gradient Estimation.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2001

Emmerald: a fast matrix-matrix multiply using Intel's SSE instructions.

[BibT_eX]

[DOI]

Concurr. Comput. Pract. Exp., 2001

A Multi-Agent Policy-Gradient Approach to Network Routing.

[BibT_eX]

Nigel Tao

Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williams College, Williamstown, MA, USA, June 28, 2001

2000

Improved Generalization Through Explicit Optimization of Margins.

[BibT_eX]

[DOI]

Llew Mason

Mach. Learn., 2000

Learning to Play Chess Using Temporal Differences.

[BibT_eX]

[DOI]

Mach. Learn., 2000

A Model of Inductive Bias Learning.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2000

98¢/Mflops/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster.

[BibT_eX]

[DOI]

Robert Edwards

Proceedings of the Proceedings Supercomputing 2000, 2000

Direct gradient-based reinforcement learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Circuits and Systems, 2000

Reinforcement Learning in POMDP's via Direct Gradient Ascent.

[BibT_eX]

Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), Stanford University, Stanford, CA, USA, June 29, 2000

General Matrix-Matrix Multiplication Using SIMD Features of the PIII (Research Note).

[BibT_eX]

[DOI]

Proceedings of the Euro-Par 2000, Parallel Processing, 6th International Euro-Par Conference, Munich, Germany, August 29, 2000

Stochastic optimization of controlled partially observable Markov decision processes.

[BibT_eX]

[DOI]

Proceedings of the 39th IEEE Conference on Decision and Control, 2000

1999

Guest Editors' Introduction.

[BibT_eX]

[DOI]

Nicolò Cesa-Bianchi

Mach. Learn., 1999

KnightCap: A chess program that learns by combining TD(lambda) with game-tree search

[BibT_eX]

[DOI]

CoRR, 1999

TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search

[BibT_eX]

[DOI]

CoRR, 1999

Boosting Algorithms as Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29, 1999

1998

Experiments in Parameter Learning Using Temporal Differences.

[BibT_eX]

[DOI]

J. Int. Comput. Games Assoc., 1998

Direct Optimization of Margins Improves Generalization in Combined Classifiers.

[BibT_eX]

[DOI]

Llew Mason

Proceedings of the Advances in Neural Information Processing Systems 11, [NIPS Conference, Denver, Colorado, USA, November 30, 1998

KnightCap: A Chess Programm That Learns by Combining TD(lambda) with Game-Tree Search.

[BibT_eX]

Proceedings of the Fifteenth International Conference on Machine Learning (ICML 1998), 1998

The Canonical Distortion Measure for Vector Quantization and Function Approximation.

[BibT_eX]

[DOI]

Proceedings of the Learning to Learn., 1998

Theoretical Models of Learning to Learn.

[BibT_eX]

[DOI]

Proceedings of the Learning to Learn., 1998

1997

A Bayesian/Information Theoretic Model of Learning to Learn via Multiple Task Sampling.

[BibT_eX]

[DOI]

Mach. Learn., 1997

The Canonical Distortion Measure in Feature Space and 1-NN Classification.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 10, 1997

The Canonical Distortion Measure for Vector Quantization and Function Approximation.

[BibT_eX]

Proceedings of the Fourteenth International Conference on Machine Learning (ICML 1997), 1997

A Result Relating Convex <i>n</i>-Widths to Covering Numbers with some Applications to Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Computational Learning Theory, Third European Conference, 1997

1996

Learning to Compress Ergodic Sources.

[BibT_eX]

[DOI]

John Shawe-Taylor

Proceedings of the 6th Data Compression Conference (DCC '96), Snowbird, Utah, USA, March 31, 1996

A Bayesian/Information Theoretic Model of Bias Learning.

[BibT_eX]

[DOI]

Proceedings of the Ninth Annual Conference on Computational Learning Theory, 1996

1995

Learning Model Bias.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 8, 1995

Learning Internal Representations.

[BibT_eX]

[DOI]