Webber, C. J. S. (1994). Self-organisation of transformation-invariant detectors for constituents of perceptual patterns. Neuro Prose.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....on the generalisation and discrimination between patterns. These two aspects are known to represent opposing trends. To generalise over a large group of patterns and at the same time discriminate between others is known to be a difficult task. In a multi layer system this conflict can be moderated [Webber, 1994] by distributing it over several processing stages. The prospect of developing a generic and extremely powerful pattern recognition system and the ability to study the processing of the human visual pathway even on an extremely simplified level, motivated researchers to proposed a number of ....

Webber, C. J. S. (1994). Self-organisation of transformation-invariant detectors for constituents of perceptual patterns. Neuro Prose.

....receives input from the whole image, via its 131,072 dimensional weight vector. Each neuron computes as its output a (softened) semi linear function r w x ( of its weight input scalar product [Figure 1] The form of non linearity r can be related analytically to component finding behaviour [3] . It is imagined that the outputs regenerate an estimate E of the input x: E a wr w x i i i = 1 2,097,152 : this reconstruction would be obtained by Bayesian folded Markov chain on the basis of a temporally long sequence of individual neural firing events of rates r w x i ( 4] ....

Webber C. J. S. Self-organisation of transformation-invariant detectors for constituents of perceptual patterns, Network: Computation in Neural Systems 5, 471-496 (1994)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC