Emergent Intelligence from Adaptive Processing Systems
The n-tuple recognition net is seen as a building brick of a progression of network structures. The emergent “intelligent” properties of such systems are discussed. They include the amplification of confidence for the recognition of images that differ in small detail, a short-term memory of the lastseen image, sequence sensitivity, sequence acceptance and saccadic inspection as an aid in scene analysis.
KeywordsEmergent Property Artificial Vision Artificial Neuron Intelligent Behaviour Sequence Sensitivity
Unable to display preview. Download preview PDF.
- 2.Minsky, M. L.; Papert S. Perceptrons: An Introduction to Computational Geometry MIT Press, Cambridge, 1969.Google Scholar
- 3.Boden, M. Artificial Intelligence and Natural Man Harvester Press, Hassocks, 1977.Google Scholar
- 4.Gregory, R. The Mind in Science Weidenfeld,Nicholson, London, 1981.Google Scholar
- 5.Aleksander, I.; Stonham, T. J.; Wilkie, R.A. Computer vision systems for industry. Digital Systems for Industrial Automation 1982, 1 (4), 305–320.Google Scholar
- 6.Brindley, G. S. The classification of modifiable synapses and their use in models for conditioning. Proceedings of the Royal Society of London, Series B 1967, 168, 361–376.Google Scholar
- 7.Uttley, A. M. Conditional computing in a nervous system. Mechanisation of Thought Processes London, 1959.Google Scholar
- 8.Aleksander, I. Memory networks for practical vision systems. Proceedings of the Rank Prize Fund International Symposium on the Physical and Biological Processing of Images London, 1982.Google Scholar
- 11.Dawson, C. Simple Scene Analysis Using Digital Learning Nets, Thesis, University of Kent, 1975.Google Scholar
- 12.Barlow, H. B. Understanding natural vision. Proceedings of the Rank Prize Fund International Symposium on the Physical and Biological Processing of Images London, 1982.Google Scholar