Many researchers interested in connectionist models accept that such models are "neurally inspired " but do not worry too much about whether their models are biologically realistic. While such a position may be perfectly justifiable, the present paper attempts to illustrate how biological information can be used to constrain connectionist models. Two particular areas are discussed. The first section deals with visual information processing in the primate and human visual system. It is argued that speed with which visual information is processed imposes major constraints on the architecture and operation of the visual system. In particular, it seems that a great deal of processing must depend on a single bottum-up pass. The second section deals with biological aspects of learning algorithms. It is argued that although there is good evidence for certain coactivation related synaptic modification schemes, other learning mechanisms, including back-propagation, are not currently supported by experimental data.

Many different algorithms and objective functions for topographic mappings have been proposed. We show that several of these approaches can be seen as particular cases of a more general objective function. Consideration of a very simple mapping problem reveals large differences in the form of the map that each particular case favors. These differences have important consequences for the practical application of topographic mapping methods.

The system presented is part of a general object recognition system. Images of faces are represented as graphs, labeled with topographical information and local features. New graphs of faces are generated by an elastic graph matching procedure comparing the new face with a composition of stored graphs: the face bunch graph. The result of this matching process can be used to generate composite images of faces and to determine facial attributes represented in the bunch graph, such as sex or the presence of glasses or a beard. Keywords: face analysis, sex discrimination, facial attributes, phantom faces, Gabor wavelets, elastic graph matching, bunch graph. 1 Introduction The system presented here has not primarily been designed for face processing or even sex identification. It is rather part of a larger effort to develop a general recognition system, which can be applied to faces [1] as well as to any other class of objects [2]. It has also been shown that it can deal with many differe...

xi 1 Introduction 1 1.1 Problem Statement : : : : : : : : : : : : : : : : : : : : : : : : : 6 1.2 The Neuron : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 7 1.2.1 Biological Model : : : : : : : : : : : : : : : : : : : : : : 7 1.2.2 Computational Model : : : : : : : : : : : : : : : : : : : 9 1.3 Implementation Technologies : : : : : : : : : : : : : : : : : : : : 11 1.4 State of the Art : : : : : : : : : : : : : : : : : : : : : : : : : : : 14 1.5 Summary of Results : : : : : : : : : : : : : : : : : : : : : : : : 16 2 Implementation of Neural Models with Static Links 19 2.1 ANN Models with Static Links : : : : : : : : : : : : : : : : : : 20 2.1.1 The Hopfield Model : : : : : : : : : : : : : : : : : : : : : 21 2.1.2 The Perceptron Model : : : : : : : : : : : : : : : : : : : 23 2.1.3 The Multi-Layer Model : : : : : : : : : : : : : : : : : : : 24 2.2 Basic Computational Requirements : : : : : : : : : : : : : : : : 25 2.2.1 Search Phase Computations : : : : : : : : : : : : : : ...

Several factors may interact to determine the periodicity of ocular dominance stripes in cat and monkey visual cortex. Previous theoretical work has suggested roles for the width of cortical interactions and the strength of between-eye correlations. Here, a model based on an explicit optimization is presented that allows a thorough characterization of how these and other parameters of the afferent input could affect ocular dominance stripe periodicity. The principle conclusions are that increasing the width of within-eye correlations leads to wider columns, and, surprisingly, that increasing the width of cortical interactions can sometimes lead to narrower columns. 1 Introduction In cats, monkeys and humans, layer 4 of the primary visual cortex (V1) is divided up into alternating regions dominated by input from the left and right eyes (e.g. Hubel & Wiesel (1977)). These regions segregate from a spatially uniform pattern during development (Rakic, 1976; LeVay et al, 1978). A characte...

The role of topographical constraints for recognition performance is investigated systematically for the case of face recognition. Images are represented by rectangular graphs labeled with jets, based on a Gabor wavelet transform. Topographical constraints are varied between rigid and free matching. A comparison with two elastic graph matching algorithms is made. The simple methods and elastic graph matching perform comparably on easy galleries, i.e. different facial expression or 11 ffi rotation in depth. On a 22 ffi gallery, elastic graph matching performs significantly better. Keywords: face recognition, Gabor wavelet transform, topographical constraints. 1 Introduction One of the main problems in face recognition is to reliably find the face and its landmarks in the first place. In practical systems most of the effort goes into solving this task, while the actual recognition based on features extracted from these facial landmarks is only a minor last step. A typical approach ...

Variable binding is a difficult problem for neural networks. Two new mechanisms for binding by synaptic change are presented, and in both, bindings are erased and can be reused. The first is based on the commonly used learning mechanism of permanent change of synaptic weight, and the second on synaptic change which decays. Both are biologically motivated models. Simulations of binding on a paired association task are shown with the first mechanism succeeding with a 97.5 % F-Score, and the second performing perfectly. Further simulations show that binding by decaying synaptic change copes with cross talk, and can be used for compositional semantics. It can be inferred that binding by permanent change accounts for these, but it faces the stability plasticity dilemma. Two other existing binding mechanism, synchrony and active links, are compatible with these new mechanisms. All four mechanisms are compared and integrated in a Cell Assembly theory. 1 1

The system presented is part of a general object recognition system. Images of faces are represented as graphs, labeled with topographical information and local features. New graphs of faces are generated by an elastic graph matching procedure comparing the new face with a composition of stored graphs: the face bunch graph. The result of this matching process can be used to generate composite images of faces and to determine facial attributes represented in the bunch graph, such as sex or the presence of glasses or a beard. Keywords: face analysis, sex discrimination, facial attributes, phantom faces, Gabor wavelets, elastic graph matching, bunch graph. 1 Introduction The system presented here has not primarily been designed for face processing or even sex identification. It is rather part of a larger effort to develop a general recognition system, which can be applied to faces (Wiskott et al. 1995) as well as to any other class of objects (Lades 1995). It has also been shown that i...

Labeled Graph Matching (LGM) has been shown successful in numerous object vision tasks. This method is the basis for arguably the best face recognition system in the world. We present an algorithm for visual pattern recognition that is an extension of LGM ("LGM + "). We compare the performance of LGM and LGM + algorithms with a state of the art statistical method based on Mutual Information Maximization (MIM). We present an adaptation of the MIM method for multi-dimensional Gabor wavelet features. The three pattern recognition methods were evaluated on an object detection task, using a set of stimuli on which none of the methods had been tested previously. The results indicate that while the performance of the MIM method operating upon Gabor wavelets is superior to the same method operating on pixels and to LGM, it is surpassed by LGM +. LGM + offers a significant improvement in performance over LGM without losing LGM’s virtues of simplicity, biological plausibility, and a computational cost that is 2-3 orders of magnitude lower than that of the MIM algorithm.

aki rendkívül sok segítséget nyújtott szakdolgozatom elkészítésében. Folyamatosan tanácsokkal látott el, gondosan és türelmesen válaszolt a felmerül® kérdéseimre, fáradhatatlanul támogatott munkámban. Hálás vagyok L®rincz Andrásnak, az egyetemen m¶köd ® NIPG csoport vezet®jének. Ž ismertetett meg a csapatmunka szellemével, az együttes alkotás örömével. Megtanított a tudományok összefonódásának fontosságára, elképeszt® munkabírása példát mutatott. Csapatának tagjaiban valódi barátokra leltem. Köszönettel tartozom az ELTE tanárainak, akik rendíthetetlenül kalauzoltak a matematika rögös ösvényein. Hálámat szeretném kifejezni szüleimnek, akik biztosították tanulmányaimhoz a családi békét, és harmóniát. Köszönet testvéremnek és parányi, huncut kislányának, kik vidámságukkal állandó fényt csempésztek életembe. 2 Tézisek 1 A retina egy közismert jellemvonása a változó mintavételezési s¶r¶ség: a középen