Search
Now showing items 1-8 of 8
A Comparative Analysis of Reinforcement Learning Methods
(1991-10-01)
This paper analyzes the suitability of reinforcement learning (RL) for both programming and adapting situated agents. We discuss two RL algorithms: Q-learning and the Bucket Brigade. We introduce a special case of the ...
Synthesis of Visual Modules from Examples: Learning Hyperacuity
(1991-01-01)
Networks that solve specific visual tasks, such as the evaluation of spatial relations with hyperacuity precision, can be eastily synthesized from a small set of examples. This may have significant implications for the ...
Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries
(1992-02-01)
In this note we discuss how recognition can be achieved from a single 2D model view exploiting prior knowledge of an object's structure (e.g. symmetry). We prove that for any bilaterally symmetric 3D object one non- ...
Task and Object Learning in Visual Recognition
(1991-01-01)
Human performance in object recognition changes with practice, even in the absence of feedback to the subject. The nature of the change can reveal important properties of the process of recognition. We report an ...
Probabilistic Independence Networks for Hidden Markov Probability Models
(1996-03-13)
Graphical techniques for modeling the dependencies of randomvariables have been explored in a variety of different areas includingstatistics, statistical physics, artificial intelligence, speech recognition, image ...
Neural Networks
(1996-03-13)
We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view ...
Interaction and Intelligent Behavior
(1994-08-01)
We introduce basic behaviors as primitives for control and learning in situated, embodied agents interacting in complex domains. We propose methods for selecting, formally specifying, algorithmically implementing, ...
On Convergence Properties of the EM Algorithm for Gaussian Mixtures
(1995-04-21)
"Expectation-Maximization'' (EM) algorithm and gradient-based approaches for maximum likelihood learning of finite Gaussian mixtures. We show that the EM step in parameter space is obtained from the gradient via a ...