A learning mechanism for invariant pattern recognition in neural networks

Coolen, Anthony C. C.; Kuijk, Fons

doi:10.1016/0893-6080(89)90046-4

Cited by 17 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Somewhat higher-level visual functions have also been shown to be learnable by SONNs: localization and length-measurement of edges [29] , detection of motion direction and velocity [25,26,[34][35][36], detection of visual rotation and dilation [4,37] , and visual depth from motion parallax [27] . The SONNs described by Marshall [25][26][27][28][29][30][31][32][33][34] combine a new inhibitory learning rule with the excitatory learning rule to produce more sophisticated network behavior.…”

Section: Self-organizing Neural Network For Orientation Detectionmentioning

confidence: 99%

<title>Adaptive neural methods for multiplexing oriented edges</title>

Marshall

1991

SPIE Proceedings

View full text Add to dashboard Cite

Edge linearization operators are often used in computer vision and in neural network models of vision to reconstruct noisy or incomplete edges. Such operators gather evidence for the presence of an edge at various orientations across all image locations and then choose the orientation that best fits the data at each point. One disadvantage of such methods is that they often function in a winner-take-all fashion: the presence of only a single orientation can be represented at any point; multiple edges cannot be represented where they intersect. For example, the neural Boundary Contour System of Grossberg and Mingolla implements a form of winner-take-all competition between orthogonal orientations at each spatial location, to promote sharpening of noisy, uncertain image data. But that competition may produce rivalry, oscillation, instability, or mutual suppression when intersecting edges (e.g., a cross) are present. This "cross problem" exists for all techniques, including Markov Random Fields, where a representation of a chosen favored orientation suppresses representations of alternate orientations.A new adaptive technique, using both an inhibitory learning rule and an excitatory learning rule, weakens inhibition between neurons representing poorly correlated orientations. It may reasonably be assumed that neurons coding dissimilar orientations are less likely to be coactivated than neurons coding similar orientations. Multiplexing by superposition is ordinarily generated: combinations of intersecting edges become represented by simultaneous activation of multiple neurons, each of which represents a single supported oriented edge. Unsupported or weakly supported orientations are suppressed. The cross problem is thereby solved.

show abstract

Section: Self-organizing Neural Network For Orientation Detectionmentioning

confidence: 99%

<title>Adaptive neural methods for multiplexing oriented edges</title>

Marshall

1991

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Many authors [ 1,2,3,5,9,16 ] have tried to solve this problem but no satisfactory general theory exists. Often, the methods are based on extracting "features" which are invariant under transformations.…”

Section: Introduccrlonmentioning

confidence: 99%

“…The main difficulty in using the conventional techniques is that they are not fault tolerant. Neural networks have been found to be fault tolerant in pattern recognition [ 3,4,5,6,7,8,9,12 ]. Fukushima and Miyaki [3] used a multilayered neural network, called "neocognitron," to recognize numerals.…”

Section: Introduccrlonmentioning

confidence: 99%

Transformations and distortions tolerant recognition of numerals using neural networks

Srivastava

1991

Proceedings of the 19th Annual Conference on Computer Science - CSC '91

View full text Add to dashboard Cite

This paper presents a multilayered artificial neural network model to recognize numerals independent of their sizes, positions, and orientations. We used a modified backpropagation algorithm to train the network.We preprocessed the numerals for "feature" extraction by calculating their moments. The moments are invariant under translation, scaling, and rotation transformations. We used the moments as input to the network rather than the digitized pattern itself. The network was able to recognize transformed and slightly deformed numerals.Parallel computational capability of the network makes it an attractive alternative for real-time commercial applications.

show abstract

“…Self-organization methods, using unsupervised learning rules, have been useful in modeling the development of several aspects of low-level visual perception, including sensitivity to contrast (Linsker, 1986a), orientation (Bienenstock, Cooper, & Munro, 1982;Linsker, 1986b;Marshall, 1990f;von der Malsburg, 1973), motion (Coolen & Kuijk, 1989;Földiák, 1991;Marshall, 1989ab, 1990aM.E. Sereno, 1986M.E.…”

mentioning

confidence: 99%

<title>Challenges of vision theory: self-organization of neural mechanisms for stable steering of object-grouping data in visual motion perception</title>

Marshall

1991

SPIE Proceedings

View full text Add to dashboard Cite

A bstract. Psychophysical studies on motion perception suggest that human visual systems perform certain nonlocal operations. In some cases, data about one part of an image can influence the processing or perception of data about another part of the image, across a long spatial range. In others, data about nearby parts of an image can fail to influence one another strongly, despite their proximity. Several types of nonlocal interaction may underlie cortical processing for accurate, stable perception of visual motion, depth, and form:. trajectory-specific propagation of computed moving stimulus information to successive image locations where a stimulus is predicted to appear;. grouping operations (establishing linkages among perceptually related data);. scission operations (breaking linkages between unrelated data); and . steering operations, whereby visible portions of a visual group or object can control the representations of invisible or occluded portions of the same group. Nonlocal interactions like these could be mediated by long-range excitatory horizontal intrinsic connections (LEHICs), discovered in visual cortex of several animal species. LEHICs often span great distances across cortical image space. Typically, they have been found to interconnect regions of like specificity with regard to certain receptive field attributes, e.g., stimulus orientation. It has recently been shown that several visual processing mechanisms can self-organize in model recurrent neural networks using unsupervised "EXIN" (excitatory+inhibitory) learning rules . Because the same rules are used in each case, EXIN networks provide a means to unify explanations of how different visual processing modules acquire their structure and function. EXIN networks learn to multiplex (or represent simultaneously) multiple spatially overlapping components of complex scenes, in a context-sensitive fashion. Modeled LEHICs have been used together with the EXIN learning rules to show how visual experience can shape neural mechanisms for nonlocal, context-sensitive processing of visual motion data.Nonlo cal Interactions Mediate Percept ual Stability.

show abstract

A learning mechanism for invariant pattern recognition in neural networks

Cited by 17 publications

References 16 publications

<title>Adaptive neural methods for multiplexing oriented edges</title>

<title>Adaptive neural methods for multiplexing oriented edges</title>

Transformations and distortions tolerant recognition of numerals using neural networks

<title>Challenges of vision theory: self-organization of neural mechanisms for stable steering of object-grouping data in visual motion perception</title>

Contact Info

Product

Resources

About