UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Schema-Based Object Recognition and Scene Analysis: The VISOR System
Active from 1993 - 1997
VISOR is a large connectionist system that shows how visual schemas can be learned, represented, and used through mechanisms natural to neural networks. Processing in VISOR is based on cooperation, competition, and parallel bottom-up and top-down activation of schema representations. Simulations show that VISOR is robust against noise and variations in the inputs and parameters. It can indicate the confidence of its analysis, pay attention to important minor differences, and use context to recognize ambiguous objects. Experiments also suggest that the representation and learning are stable, and its behavior is consistent with human processes such as priming, perceptual reversal, and circular reaction in learning. The schema mechanisms of VISOR can serve as a starting point for building robust high-level vision systems, and perhaps for schema-based motor control and natural language processing systems as well.
People
Wee Kheng Leow
Ph.D. Alumni
leowwk [at] comp nus edu sg
Publications
Visual Schemas In Neural Networks For Object Recognition And Scene Analysis
1997
Wee Kheng Leow, Risto Miikkulainen,
Connection Science
Michael A. Arbib (Eds.) (1997), pp. 1029-1031. MIT Press.
Visual Schemas In Object Recognition And Scene Analysis
1995
Risto Miikkulainen and Wee Kheng Leow, In
The Handbook of Brain Theory and Neural Networks
, M. A. Arbib (Eds.), pp. 1029--1031, Cambridge, MA 1995. MIT Press.
Priming, Perceptual Reversal, And Circular Reaction In A Neural Network Model Of Schema-Based Vision
1994
Wee Kheng Leow and Risto Miikkulainen, In
Proceedings of the 16th Annual Conference of the Cognitive Science Society
, Ashwin Ram and Kurt Eiselt (Eds.), pp. 560-565 1994. Hillsdale, NJ: Erlbaum.
Representing And Learning Visual Schemas In Neural Networks For Scene Analysis
1994
Wee Kheng Leow and Risto Miikkulainen, In
Proceedings of the Workshop on Neural Architectures and Distributed {AI}: {F}rom Schema Assemblages to Neural Networks
, pp. 35-40, Los Angeles 1994. Center for Neural Engineering, Universit...
VISOR: Learning Visual Schemas In Neural Networks For Object Recognition And Scene Analysis
1994
Wee Kheng Leow, PhD Thesis, Department of Computer Sciences, The University of Texas at Austin. 198 pages. Technical Report AI-94-219.
VISOR: Schema-Based Scene Analysis With Structured Neural Networks
1994
Wee Kheng Leow and Risto Miikkulainen,
Neural Processing Letters
, Vol. 1 (1994), pp. 18--23.
Representing Visual Schemas in Neural Networks for Scene Analysis
1993
Wee Kheng Leow and Risto Miikkulainen, In
Proceedings of the IEEE Conference on Neural Networks (ICNN-93)
, pp. 1612-1617, San Francisco, CA 1993. Piscataway, NJ: IEEE.
Related Areas
Concept and Schema Learning
Labs
Neural Networks