Abstract|We present an object recognition system based

We study image segmentation on the basis of locally excitatory globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a potential for each oscillator so that only those oscillators with strong connections from their neighborhood can develop high potentials. Based on the concept of potential, a solution to remove noisy regions in an image is proposed for LEGION, so that it suppresses the oscillators corresponding to noisy regions, without affecting those corresponding to major regions. We show analytically that the resulting oscillator network separates an image into several major regions, plus a background consisting of all noisy regions, and illustrate network properties by computer simulation. The network exhibits a natural capacity in segmenting images. The oscillatory dynamics leads to a computer algorithm, which is applied successfully to segmenting real graylevel images. A number of issues regarding biological plausibility and perceptual organization are discussed. We argue that LEGION provides a novel and effective framework for image segmentation and figure-ground segregation. DeLiang Wang and David Terman Image Segmentation 1.

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which object they belong. Current computational systems that perform this operation are based on predefined grouping heuristics. We describe a system called MAGIC that learns how to group features based on a set of presegmented examples. In many cases, MAGIC discovers grouping heuristics similar to those previously proposed, but it also has the capability of finding nonintuitive structural regularities in images. Grouping is performed by a relaxation network that attempts to dynamically bind related features. Features transmit a complex-valued signal (amplitude and phase) to one another; binding can thus be represented by phase locking related features. MAGIC's training procedure is a generalizatio...

2 Abstract We investigate the computational power of a formal model for networks of spiking neurons. It is shown that simple operations on phase-differences between spike-trains provide a very powerful computational tool that can in principle be used to carry out highly complex computations on a small network of spiking neurons. We construct networks of spiking neurons that simulate arbitrary threshold circuits, Turing machines, and a certain type of random access machines with real valued inputs. We also show that relatively weak basic assumptions about the response- and threshold-functions of the spiking neurons are sufficient in order to employ them for such computations. Furthermore we prove upper bounds for the computational power of networks of spiking neurons with arbitrary piecewise linear responseand threshold-functions, and show that they are with regard to realtime simulations computationally equivalent to a certain type of random access machine, and to recurrent analog neural nets with piecewise linear activation functions. In addition we give corresponding results for networks of spiking neurons with a limited timing precision, and we prove upper and lower bounds for the VC-dimension and pseudo-dimension of networks of spiking neurons. 3 1

Relaxation oscillations exhibiting more than one time scale arise naturally from many physical systems. This paper proposes a method to numerically integrate large systems of relaxation oscillators. The numerical technique, called the singular limit method, is derived from analysis of relaxation oscillations in the singular limit. In such limit, system evolution gives rise to time instants at which fast dynamics takes place and intervals between them during which slow dynamics takes place. A full description of the method is given for LEGION (locally excitatory globally inhibitory oscillator networks), where fast dynamics, characterized by jumping which leads to dramatic phase shifts, is captured in this method by iterative operation and slow dynamics is entirely solved. The singular limit method is evaluated by computer experiments, and it produces remarkable speedup compared to other methods of integrating these systems. The speedup makes it possible to simulate large-scale oscillato...

Throughout the early history of neurology and neuroscience, most theoretical accounts of brain function have emphasized either aspects of localization or distributed properties [1]. Instead, modern views focus extensively on the structure and dynamics of large-scale neuronal networks, especially those of the cerebral cortex and associated thalamocortical

Systems with large amounts of computing power and storage are required to simulate very large neural networks capable of tackling complex control problems and real-time emulation of the human sensory, language and reasoning systems. General-purpose parallel computers do not have communications, processor and memory architectures optimized for neural computation and so can not perform such simulations at reasonable cost. This thesis analyses several software and hardware strategies to make feasible the simulation of large, brain-like neural networks in real-time, and presents a particular multicomputer design able to implement these strategies. An important design goal is that the system must not sacrifice computational flexibility for speed, as new information about the workings of the brain and new artificial neural network architectures and learning algorithms are continually emerging. The main contributions of the thesis are: --- an analysis of the important features of biological n...

Understanding how biological visual systems perform object recognition is one of the ultimate goals in computational neuroscience. Among the biological models of recognition the main distinctions are between feedforward and feedback and between object-centered and view-centered. From a computational viewpoint the different recognition tasks --- for instance categorization and identification --- are very similar, representing different trade-offs between specificity and invariance. Thus the different tasks do not strictly require different classes of models. The focus of the review is on feedforward, view-based models that are supported by psychophysical and physiological data.

Abstract: We present the implementation of on-line Hebbian learning for NESPINN, the Neurocomputer for the simulation of spiking neurons. In order to support various forms of Hebbian learning we developed a programmable weight unit for the NESPINN-system. On-line weight modifications are performed event-controlled in parallel to the computation of basic neuron functions. According to our VHDL-simulations, the system will offer a performance of up to 50 MCUPS. 1

As a benchmark task, the spiral problem is well known in neural networks. Unlike previous work that emphasizes learning, we approach the problem from a generic perspective that does not involve learning. We point out that the spiral problem is intrinsically connected to the inside /outside problem. A generic solution to both problems is proposed based on oscillatory correlation using a time delay network. Our simulation results are qualitatively consistent with human performance, and we interpret human limitations in terms of synchrony and time delays, both biologically plausible. As a special case, our network without time delays can always distinguish these figures regardless of shape, position, size, and orientation. We conjecture that visual perception will be effortful if local activation cannot be rapidly propagated, as synchrony would not be established in the presence of time delays. 1 INTRODUCTION The spiral problem refers to distinguishing between a connected single spiral a...