20 March 2001 Optical pattern recognition algorithms on neural-logic equivalent models and demonstration of their prospects and possible implementations
Author Affiliations +
Abstract
Historic information regarding the appearance and creation of fundamentals of algebra-logical apparatus-`equivalental algebra' for description of neuro-nets paradigms and algorithms is considered which is unification of theory of neuron nets (NN), linear algebra and the most generalized neuro-biology extended for matrix case. A survey is given of `equivalental models' of neuron nets and associative memory is suggested new, modified matrix-tenzor neurological equivalental models (MTNLEMS) are offered with double adaptive-equivalental weighing (DAEW) for spatial-non- invariant recognition (SNIR) and space-invariant recognition (SIR) of 2D images (patterns). It is shown, that MTNLEMS DAEW are the most generalized, they can describe the processes in NN both within the frames of known paradigms and within new `equivalental' paradigm of non-interaction type, and the computing process in NN under using the offered MTNLEMs DAEW is reduced to two-step and multi-step algorithms and step-by-step matrix-tenzor procedures (for SNIR) and procedures of defining of space-dependent equivalental functions from two images (for SIR).
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Vladimir G. Krasilenko, Vladimir G. Krasilenko, Alexander I. Nikolsky, Alexander I. Nikolsky, Alexandr V. Zaitsev, Alexandr V. Zaitsev, Victor M. Voloshin, Victor M. Voloshin, } "Optical pattern recognition algorithms on neural-logic equivalent models and demonstration of their prospects and possible implementations", Proc. SPIE 4387, Optical Pattern Recognition XII, (20 March 2001); doi: 10.1117/12.421146; https://doi.org/10.1117/12.421146
PROCEEDINGS
14 PAGES


SHARE
Back to Top