Publications by Leemon Baird
Home | Machine Learning | Crypto | Graphics
Publications | Concise Pubs | BibTeX Pubs | Other Pubs | WebSim

Most of my publications are available in PDF, Postscript and HTML, each with its source file (either LaTeX or RTF (Microsoft Word)). This bibliography can be listed in several different formats. Please tell me if there are any problems downloading or viewing them.

17 Feb 2005


In:pdf:ps:#p:Title:
Patent  2004      21  US Patent #6,732,278: Apparatus and method for authenticating access to a network resource
IJCAI  1999  pdf  ps.gz  Multi-Value-Functions: Efficient Automatic Action Hierarchies for Multiple Goal MDPs
IJCNN  1999  pdf  ps.gz  Gradient Descent Approaches to Neural-Net-Based Solutions of the Hamilton-Jacobi-Bellman Equation
NIPS  1999  pdf  ps.gz  Gradient descent for general reinforcement learning
TR  1999  pdf  ps.gz  78  Reinforcement Learning Through Gradient Descent
TNN  1998  pdf  ps.gz  23  An Analytical Framework for Local Feedforward Networks
ISIC  1998  pdf  ps.gz  Preventing unlearning during on-line training of feedforward networks
Patent  1997      25  US Patent #5,608,843: Learning controller with advantage updating algorithm
Crosstalk  1996  pdf  ps.gz  Reinforcement Learning: An Alternative Approach to Machine Intelligence
ICML  1996  pdf  ps.gz  10  Residual Q-learning applied to visual attention
ISIC  1996  pdf  ps.gz  An analytical framework for local feedforward networks
ADPC  1996  pdf  ps.gz  11  Local feedforward networks
TR  1996  pdf  ps.gz  Spurious Solutions to the Bellman Equation
TR  1996  pdf  ps.gz  Metrics for Temporal Difference Learning
TR  1996  pdf  ps.gz  12  Multi-player residual advantage learning with general function approximation
ABJ  1995  pdf  ps.gz  28  Reinforcement Learning Applied to a Differential Game
ICML  1995  pdf  ps.gz  Residual Algorithms: Reinforcement Learning with Function Approximation
ICML-VFA  1995  pdf    Residual Algorithms
ICNN  1995  pdf  ps.gz  Residual Advantage Learning Applied to a Differential Game
ACC  1995  pdf  ps.gz  On the Localization of Feedforward Networks
NIPS  1995  pdf  ps.gz  10  Advantage Updating Applied to a Differential Game
ICNN  1994  pdf  ps.gz  Reinforcement Learning in Continuous Time: Advantage Updating
YWALS  1994  pdf  ps.gz  Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions
TR  1993  pdf  ps.gz  48  Advantage Updating
TR  1993  pdf  ps.gz  19  Reinforcement Learning with High-Dimensional, Continuous Actions
TR  1993  pdf  ps.gz  49  Analysis of Some Incremental Variants of Policy Iteration: First Steps Toward Understanding Actor-Critic Learning Systems
TR  1993  pdf  ps.gz  20  Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions
SMC  1992  pdf  ps.gz  Function Minimization for Dynamic Programming Using Connectionist Networks
YWALS  1990  pdf  ps.gz  A Mathematical Analysis of Actor-Critic Architectures for Learning Optimal Controls Through Incremental Dynamic Programming
JMIV  1995        3-D object perception using gradient descent
JMP  1994        Reinforcement learning and optimal decision making
ABJ  1993        A hierarchical network of provably optimal learning control systems: Extensions of the associative control process (ACP) network
SAB  1993        Extensions of the associative control process (ACP) network: Hierarchies and provable optimality
TR  1993        Investigation of Drive-Reinforcement Learning and Application of Learning to Flight Control
IRCV  1991        3D object recognition using gradient descent and the universal 3D ray grammar
SCS  1991        A design and simulation tool for connectionist learning control systems: Application to autonomous underwater vehicles
TR  1991        Learning and adaptive hybrid systems for nonlinear control
GNC  1990        A connectionist learning system for nonlinear control
In:= Link to the full reference for the paper, and other downloadable files.
pdf= Link to the Adobe Acrobat form of the paper.
ps= Link to the Poscript form of the paper.
#p= Number of pages in the Poscript paper.
Title= Link to the paper converted to a Web page.
ABJ= Adaptive Behavior Journal
ACC= American Control Conference
ADPC= Adaptive Distributive Parallel Computing Conference
GNC= AIAA Conference on Guidance, Navigation, and Control
ICML= International Conference on Machine Learning
ICML-VFA= ICML Workshop on Value Function Approximation
ICNN= International Conference on Neural Networks
IJCAI= International Joint Conference on Artificial Intelligence
IJCNN= International Joint Conference on Neural Networks
IRCV= SPIE Conference on Intelligent Robots and Computer Vision
ISIC= International Symposium of Intelligent Control
JMIV= Journal of Mathematical Image and Vision
JMP= Journal of Mathematical Psychology
NIPS= Neural Information Processing Systems Conference
SAB= International Conference on Simulation of Adaptive Behavior
SCS= Proceedings of the Society for Computer Simulation Conference
SMC= IEEE Conference on Systems Man and Cybernetics
TNN= IEEE Transactions on Neural Networks
TR= Technical Report
YWALS= Yale Workshop on Adaptive and Learning Systems