Pattern segmentation in a binary/analog world: unsupervised learning versus memory storing

Lourenço, Carlos; Babloyantz, Agnessa; Hougardy, Marc

doi:10.1016/s0893-6080(99)00087-8

Cited by 5 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More advanced models [27], [41], [55] address the scene analysis problem via multilayer systems, encompassing initial primitive segmentation and associative memory: objects are first segmented at an early processing layer by using low-level spatial rules, then the segmented objects are sent to a memory layer which performs recognition and learns new memories. Some models based on oscillators synchronization have been proposed with application to the problem of segmentation, recognition, and memorization of odors in the olfactory system [34], [37], [46], [53]. Wang et al [53] proposed a model for sensory segmentation in which connections among oscillators encode prior knowledge, but dynamical learning was lacking.…”

Section: Introductionmentioning

confidence: 99%

“…The work by Hoshino et al [37] introduces a law of synaptic modifications and considers the problem of recognizing previously learned odors, but not segmentation (i.e., the network deals with one input at a time). Odors segmentation and learning of new patterns are addressed in a single model by Hendin and by Lourenceo et al [34], [46]. Finally, some papers by Horn et al [35], [36], [44] investigated the properties of binding, segmentation, and learning in oscillatory neural networks both by simulations and analytical calculations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Abstract Objects Via Neural Oscillators: Interaction Among Topological Organization, Associative Memory and Gamma Band Synchronization

Ursino

Magosso

Cuppini

2009

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Synchronization of neural activity in the gamma band is assumed to play a significant role not only in perceptual processing, but also in higher cognitive functions. Here, we propose a neural network of Wilson-Cowan oscillators to simulate recognition of abstract objects, each represented as a collection of four features. Features are ordered in topological maps of oscillators connected via excitatory lateral synapses, to implement a similarity principle. Experience on previous objects is stored in long-range synapses connecting the different topological maps, and trained via timing dependent Hebbian learning (previous knowledge principle). Finally, a downstream decision network detects the presence of a reliable object representation, when all features are oscillating in synchrony. Simulations performed giving various simultaneous objects to the network (from 1 to 4), with some missing and/or modified properties suggest that the network can reconstruct objects, and segment them from the other simultaneously present objects, even in case of deteriorated information, noise, and moderate correlation among the inputs (one common feature). The balance between sensitivity and specificity depends on the strength of the Hebbian learning. Achieving a correct reconstruction in all cases, however, requires ad hoc selection of the oscillation frequency. The model represents an attempt to investigate the interactions among topological maps, autoassociative memory, and gamma-band synchronization, for recognition of abstract objects.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recognition of Abstract Objects Via Neural Oscillators: Interaction Among Topological Organization, Associative Memory and Gamma Band Synchronization

Ursino

Magosso

Cuppini

2009

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…As discussed at the beginning of this section, the familiarity principle of grouping requires a memory recall and may be viewed as a top-down process. Memory-based segmentation has been previously studied [57], [65], [77], [120], [145]. But, without a primitive segmentation stage, the computational performance of these models is very limited.…”

Section: G Further Remarksmentioning

confidence: 99%

The Time Dimension for Scene Analysis

Wang

2005

IEEE Trans. Neural Netw.

107

View full text Add to dashboard Cite

A fundamental issue in neural computation is the binding problem, which refers to how sensory elements in a scene organize into perceived objects, or percepts. The issue of binding is hotly debated in recent years in neuroscience and related communities. Much of the debate, however, gives little attention to computational considerations. This review intends to elucidate the computational issues that bear directly on the binding issue. The review starts with two problems considered by Rosenblatt to be the most challenging to the development of perceptron theory more than 40 years ago, and argues that the main challenge is the figure-ground separation problem, which is intrinsically related to the binding problem. The theme of the review is that the time dimension is essential for systematically attacking Rosenblatt's challenge. The temporal correlation theory as well as its special form--oscillatory correlation theory-is discussed as an adequate representation theory to address the binding problem. Recent advances in understanding oscillatory dynamics are reviewed, and these advances have overcome key computational obstacles for the development of the oscillatory correlation theory. We survey a variety of studies that address the scene analysis problem. The results of these studies have substantially advanced the capability of neural networks for figure-ground separation. A number of issues regarding oscillatory correlation are considered and clarified. Finally, the time dimension is argued to be necessary for versatile computing.

show abstract

“…1(c), the same input that is shifted two pixels to the right leads to a wrong recall. Efforts have been made to address the segmentation problem; in particular, many models of oscillatory associative memory have been proposed to achieve the recall of multiple patterns [8], [18], [30], [42] (for a nonoscillatory example see [19]). Compared to traditional associative memory based on attractor dynamics, oscillator networks are based on limit-cycle dynamics and introduce an additional degree of freedom-time.…”

Section: Introductionmentioning

confidence: 99%

Scene analysis by integrating primitive segmentation and associative memory

Wang

Liu

2002

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage with a model of associative memory. The model is a multistage system that consists of an initial primitive segmentation stage, a multimodule associative memory, and a short-term memory (STM) layer. Primitive segmentation is performed by a locally excitatory globally inhibitory oscillator network (LEGION), which segments the input scene into multiple parts that correspond to groups of synchronous oscillations. Each segment triggers memory recall and multiple recalled patterns then interact with one another in the STM layer. The STM layer projects to the LEGION network, giving rise to memory-based grouping and segmentation. The system achieves scene analysis entirely in phase space, which provides a unifying mechanism for both bottom-up analysis and top-down analysis. The model is evaluated with a systematic set of three-dimensional (3-D) line drawing objects, which are arranged in an arbitrary fashion to compose input scenes that allow object occlusion. Memory-based organization is responsible for a significant improvement in performance. A number of issues are discussed, including input-anchored alignment, top-down organization, and the role of STM in producing context sensitivity of memory recall.

show abstract

Pattern segmentation in a binary/analog world: unsupervised learning versus memory storing

Cited by 5 publications

References 46 publications

Recognition of Abstract Objects Via Neural Oscillators: Interaction Among Topological Organization, Associative Memory and Gamma Band Synchronization

Recognition of Abstract Objects Via Neural Oscillators: Interaction Among Topological Organization, Associative Memory and Gamma Band Synchronization

The Time Dimension for Scene Analysis

Scene analysis by integrating primitive segmentation and associative memory

Contact Info

Product

Resources

About