Increasing the Power of Connectionist Networks (CN) by Improving Structures, Processes, Learning

References

• Buell , S.J. and Colemann , P.D. ( 1981 ) Quantitative evidence for selective dendritic growth in normal human aging but not in senile dementia. Brain Research , 214 , 23 – 41 .
   PubMed Web of Science ®Google Scholar
• Feldman , J.A. ( 1982 ) Dynamic connections in neural networks. , Biological Cybernetics , 46 , 27 – 39 .
   Google Scholar
• Greenough , W.T. , Juraska , J.M. and Volkmar , F.R. ( 1979 ) Maze training effects on dendritic branching in occipital cortex of adult rats. Behavioral and Neural Boiology , 26 , 287 – 297 .
   PubMedGoogle Scholar
• Greenough , W.T. , Black , J.E. and Wallace , C.S. ( 1987 ) Experience and brain development. Child Development , 58 , 533 – 559 .
   PubMed Web of Science ®Google Scholar
• Greenough , W.T. and Bailey , C.H. ( 1988 ) The anatomy of a memory: convergence of results across a diversity of tests. Trends in Neuroscience , 11 , 142 – 147 .
   Web of Science ®Google Scholar
• Grossberg , S. ( 1981 ) Adaptive resonance in development, perception and cognition. SIAM-AMS Proceedings , 13 , 107 – 155 .
   Google Scholar
• Hinton , G.E. , Sejnowski , T.J. and Ackley , D.H. ( 1984 ) Boltzmann machines: constraint satisfaction networks that learn. , Carnegie-Mellon University. Computer Science Department Technical Report 84-119,
   Google Scholar
• Honavar , V. ( 1989 ) Perceptual Development and Learning: From Behavioral, Neurophysiological, and Morphological Evidence to Computational Models. , Computer Sciences Technical Report 818, University of Wisconsin-Madison.
   Google Scholar
• Hooavar , V. and Uhr , L. ( 1988 ) A Network of Neuron— like Units that Learns to Perceive by Generation as well as Reweighting of its Links. In Proceedings 1988 Connectionist Models Summer School. , Los Altos , CA : Morgan Kaufman.
   Google Scholar
• Honavar , V. and Uhr , L. ( 1989 ) Experimental results indicate that generation, local receptive fields and global convergence improve perceptual learning in connectionist networks. Computer Sciences Department Technical Report 805 (1988). University of Wisconsin-Madison. Also in Proceedings 1989 International Joint Conference on Artificial Intelligence, 1989. ,
   Google Scholar
• Kuffler , S.W. , Nicholls , J.G. and Martin , A.R. ( 1984 ) From Neuron to Brain , 2nd edn. Sunderland , MA : Sinauer.
   Google Scholar
• Li , Z.N. and Uhr , L. ( 1987 ) Pyramid vision using key features to integrate image-driven bottom-up and model-driven top-down processes. IEEE Trans. Systems, Man and Cyber. , 16 , 250 – 262 .
   Google Scholar
• McCulloch , W.S. ( 1965 ) Embodiments of Mind. , Cambridge , MA : MIT Press.
   Google Scholar
• McCulloch , W.S. and Pitts , W. ( 1943 ) A logical calculus if the ideas immanent in nervous activity. Bulleting of Mathematical Biophysics , 5 , 115 – 133 .
   Google Scholar
• Parberry , I. ( 1989 ) A primer on the complexity theory of neural networks. A Sourcebook on Formal Techniques in Artificial Intelligence. , New York : Elsevier.
   Google Scholar
• Petri , C.A. ( 1979 ) Introduction to general net theory. In W. Brauer (Ed.) Net Theory and Applications , pp. 1 – 19 . Berlin : Springer-Verlag.
   Google Scholar
• Rosenblatt , F. ( 1962 ) Principles of Neurodynamics. , New York : Spartan Books.
   Google Scholar
• Rumelhart , D.E. and McClelland , J.L. ( 1986 ) Parallel Distributed Processing: Explorations in the Microstructure of Cognition , Vol. 1 , Foundations. Cambridge , MA : MIT Press.
   Google Scholar
• Sejnowski , T.J. and Rosenberg , C.R. ( 1987 ) Parallel networks that learn to pronouce English text. Complex Systems , 1 , 145 – 168 .
   Google Scholar
• Shastri , L. Evidential reasoning in semantic networks: a formal theory and its parallel implementation. , University of Rochester. ( 1985 ) Unpublished PhD thesis (Computer Science Department Technical Report 166),
   Google Scholar
• Turing , A.M. ( 1936 ) On computable numbers, with an application to the Entscheidungsproblem. Proceedings London Mathematical Society, Ser. , 2 , 42 , 230 – 265 .
   Google Scholar
• Turing , A.M. ( 1950 ) Computing machinery and intelligence. Mind , 59 , 433 – 460 .
   Google Scholar
• Uhr , L. ( 1978 ) 'Recognition cones' and some test results. In A. Hanson and E. Riseman (Eds) Computer Vision Systems , pp. 363 – 372 . New York : Academic Press.
   Google Scholar
• Uhr , L. ( 1986 ) Toward an information-processing computational model of object perception. , Computer Science Department Technical Report 651, University of Wisconsin.
   Google Scholar
• Uhr , L. ( 1987 a) Highly parallel, hierarchical, recognition cone perceptual structures. In L. Uhr (Ed.) Parallel Computer Vision , 4 , 249 – 292 . New York : p:Academic Press.
   Google Scholar
• Uhr , L. ( 1987 b) Multi-Computer Architectures for Artificial Ingelligence: Toward Fast, Robus, Parallel Systems. , New York : Wiley.
   Google Scholar
• Uhr , L. ( 1989 a) Giving connectionist networks the large additional sub-nets needed to handle learning (paper in preparation).
   Google Scholar
• Uhr , L. ( 1989 b) Extraction-generation can substantially improve learning in connectionist networks (CN) (paper in preparation).
   Google Scholar
• Uhr , L. ( 1989 c) Specifying useful micro-circuit structures for connectionist networks (paper in preparation).
   Google Scholar
• Uhr , L. ( 1989 d) Generating, and generalizing generations, in connectionist networks (paper in preparation).
   Google Scholar
• Uhr , L. ( 1989 c) Connectionist networks that handle symbols as well as numbers (paper in preparation).
   Google Scholar
• Uhr , L. ( 1989 f) Connectionist networks defined generally, to show where power can be increased (paper in preparation).
   Google Scholar
• Uhr , L. ( 1989 g) Generation + extraction gives optimal space-time learning of Boolean functions (including X-OR) (paper in preparation).
   Google Scholar
• Uhr , L. and Vossler , C. A pattern-recognition program that generates, evaluates and adjusts its own operators. Proceedings Western Joint Computer Conference , 19 ( 1961 ) New York : McGraw-Hill.] 555 – 570 . [Reprinted, with additional test results, in E. Feigenbaum and J. Feldman (Eds) Computers and Thought ( 1963
   Google Scholar