A self-learning visual pattern explorer and recognizer using a higher order neural network
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 705-710
- https://doi.org/10.1109/ijcnn.1992.227069
Abstract
A proposal by M. B. Reid et al. (1989) to improve the efficiency of higher-order neural networks was built into a pattern recognition system that autonomously learns to categorize and recognize patterns independently of their position in an input image. It does this by combining higher-order with first-order networks and the mechanisms known from ART. Its recognition is based on a 16×16 pixel input which contains a section of the image found by a separate centering mechanism. With this system position invariant recognition can be implemented efficiently, while combining all the advantages of the subsystems Author(s) Linhart, G. Austrian Res. Inst. for Artificial Intelligence, Vienna, Austria Dorffner, G.Keywords
This publication has 4 references indexed in Scilit:
- A massively parallel architecture for a self-organizing neural pattern recognition machinePublished by Elsevier ,2005
- Learning Sensory-Motor Coordination by Experimentation and Reinforcement LearningPublished by Springer Nature ,1990
- Self-organizing neural network architectures for computing visual depth from motion parallaxPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- An interactive activation model of context effects in letter perception: I. An account of basic findings.Psychological Review, 1981