Abstract
Most connectionist research has focused on learning mappings from one space to another (eg. classification and regression). This paper introduces the more general task of learning constraint surfaces. It describes a simple but powerful architecture for learning and manipulating nonlinear surfaces from data. We demonstrate the technique on low dimensional synthetic surfaces and compare it to nearest neighbor approaches. We then show its utility in learning the space of lip images in a system for improving speech recognition by lip reading. This learned surface is used to improve the visual tracking performance during recognition.
Keywords
Computer scienceArtificial intelligenceConstraint (computer-aided design)ConnectionismMachine learningSpace (punctuation)k-nearest neighbors algorithmPattern recognition (psychology)Task (project management)Speech recognitionArtificial neural networkMathematicsEngineering
Affiliated Institutions
Related Publications
Convex Optimization
Convex optimization problems arise frequently in many different fields. A comprehensive introduction to the subject, this book shows in detail how such problems can be solved nu...
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization.
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative grad...
Publication Info
- Year
- 1993
- Type
- article
- Volume
- 6
- Pages
- 43-50
- Citations
- 88
- Access
- Closed
External Links
Citation Metrics
88
OpenAlex
Cite This
Christoph Bregler,
Stephen M. Omohundro
(1993).
Surface Learning with Applications to Lipreading.
, 6
, 43-50.