scispace - formally typeset
Journal ArticleDOI

Selected M-Related Dissertations Bibliography

Reads0
Chats0
TLDR
The following are citations selected by title and abstract as being related to AI, resulting from a computer search, using DIALOG Information Services, of the Dissertation Abstracts Online database produced by University Microfilms International (UMI).
References
More filters

Using dynamic programming for solving variational problems in vision: applications involving deformable models for contours and surfaces.

TL;DR: In this paper, the authors apply dynamic programming to the energy-minimizing active contours optimization problem, which is set up as a discrete multistage decision process and is solved by a time-delayed discrete dynamic programming algorithm.
Book

Learning in Embedded Systems

TL;DR: This dissertation addresses the problem of designing algorithms for learning in embedded systems using Sutton's techniques for linear association and reinforcement comparison, while the interval estimation algorithm uses the statistical notion of confidence intervals to guide its generation of actions.
Journal ArticleDOI

A mathematical treatment of defeasible reasoning and its implementation

TL;DR: This thesis presents a formally precise, elegant, clean, well-defined system which exhibits a correct behavior when applied to the benchmark examples in the literature and represents a definite improvement over past systems.
Book

A Taxonomy for Texture Description and Identification

TL;DR: The taxonomy for texture can serve as a scheme for the identification and description of surface flaws and defects occurring in a wide range of practical applications.
Journal ArticleDOI

Artificial neural network models for knowledge representation in chemical engineering

TL;DR: The characteristics of neural networks desirable for knowledge representation in chemical engineering processes are described, a neural network design and simulation environment that can be used for experimentation is described, and how an artificial neural network can learn and discriminate successfully among faults is demonstrated.
Related Papers (5)