Bio-computational model of object-recognition: Quantum Hebbian processing with neurally shaped Gabor wavelets

被引：8

作者：

Perus, M

Bischof, H

Loo, CK ^{[1
]}

机构：

[1] Multimedia Univ, Fac Engn & Technol, MY-75450 Melaka, Malaysia

[2] Graz Univ Technol, Inst Comp Vis & Graph, A-8010 Graz, Austria

来源：

BIOSYSTEMS | 2005年 / 82卷 / 02期

关键词：

vision; object-recognition; quantum; Gabor wavelets; Griniasty et al; temporal sequences; holography; ICA;

D O I：

10.1016/j.biosystems.2005.06.004

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Theoretical and simulational evidence, as well as experimental indications, are accumulating that quantum associative memory and imaging are possible. We compare these data with biological evidence. since we find them to a significant extent compatible. This paper presents a computationally implementable integrative model of appearance-based viewpoint-invariant recognition of objects. The neuro-quantum hybrid model incorporates neural processing up to VI and quantum associative processing in VI, achieving together an object-recognition result in V2 and ITC. Results of our simulation of the central quantum-like parts of the bio-model, receiving neurally pre-processed inputs, are presented. This part contains our original simulated storage by multiple quantum interference of image-encoding Gabor wavelets done in a Hebbian way, especially using the Griniasty et al. pose-sequence learning rule. (c) 2005 Elsevier Ireland Ltd. All rights reserved.

引用

页码：116 / 126

页数：11

共 81 条

[51]

Perus M., 2001, Informatica, V25, P575

[52]

Perus M., 2001, Nonlinear Phenomena in Complex Systems, V4, P157

[53]

Perus M., 2000, Neural Network World, V10, P1001

[54]

PERUS M, IN PRESS HUMAM IMAGE