EℓI-chan for Intermediate Features
Conference Proceeding Article
We propose an EℓI-chan, Emergent ℓocal Indicator Mechanism, to model the representation and self-organization of intermediate features in the visual pathway. This model is motivated by the orientation specificity in the primary visual cortex. Our simulations of EℓI-chan demonstrate that local indicators of the locations of intermediate features emerge, and they become the seeds for unsupervised learning and pattern recognition; EℓI-chan predicts those portions of the input imagery where intermediate features potentially exist. Hence, EℓI-chan can be used to define a set of intermediate features for adaptation, and the onwards processing in a hierarchical pattern recognition system.
Physical Sciences and Mathematics
Strategy and Organisation
IJCNN '93 Nagoya: Proceedings of the International Joint Conference on Neural Networks, 25-29 October 1993, Japan
City or Country
EℓI-chan for Intermediate Features. (1993). IJCNN '93 Nagoya: Proceedings of the International Joint Conference on Neural Networks, 25-29 October 1993, Japan. 2508-2511. Research Collection Lee Kong Chian School Of Business.
Available at: http://ink.library.smu.edu.sg/lkcsb_research/779