A physiologically motivated model of illusory contour perception is examined by simulating a neural network architecture that was tested with gray-level images. The results indicate that a model that combines a bottom-up feature aggregation strategy with recurrent processing is best suited for describing this type of perceptual completion.>

To discount effects of uneven illumination we have designed and tested a neural network that can adaptively control light sensitivity at the photosensor level. Our neural network architecture simulates the ON channel response of the visual system using multiple layers of hexagonally arranged nodes having partially overlapping receptive fields of different spatial frequencies. Feedforward connections are excitatory while feedback pathways subserve lateral inhibition. The outputs of these nodes are combined so as to maximize the signal to noise ratio while providing constant feedback that resets photosensor thresholds to maintain high sensitivity. A sparse primitive interpolation technique was applied to the ensemble output of the sensitivity control module to determine if it sufficiently encodes surface reflectance. The motivation is to determine to what extent the ratio principle, as captured by the sensitivity control system, explains the lightness constancy phenomenon and whether information contained within an ON channel response is adequate to reconstruct the surface lightness. Our connectionist architecture can account for many characteristics attributed to the lightness constancy phenomenon observed in biological systems. The results suggest that our module maintains high sensitivity across a large range of intensities without interfering with the transmission of visual information embedded in the spatial discontinuities of intensity. However, the amplitude of the luminance derivative as encoded in ON channel responses is not sufficient to approximate surface reflectance.

UCLA-SFINX is a neural network simulation environment that enables users to simulate a wide variety of neural network models at various levels of abstraction. A network specification language enables users to construct arbitrary network structures. Small, structurally irregular networks can be modeled by explicitly defining each neuron and can be modeled by explicitly defining each neuron and corresponding connections. Very large networks with regular connectivity patterns can be implicitly specified using array constructs. Graphics support, based on X Windows System, is provided to visualize simulation results. Details of the simulation environment are described, and simulation examples are presented to demonstrate SFINX's capabilities.>

Categorization, as an active phase of the visual perception, must include a stage where a currently viewed exemplar of an object is compared to the previously acquired category representatives; comparisons between exemplars as opposed to simply examining one exemplar in isolation lead to improved supervised learning. An abstract model of a neuron (SD neuron) is introduced, that can compare inputs by detecting (S)imilarities and (D)issimilarities in sequentially presented stimuli. Using SD neurons in a traditional Back Error Propagation (BP) neural networks improves categorization and learning capability. The nonlinear combination of similar and dissimilar input features captures more extensive information about stimulus. SD networks also display more effective convergence properties than BP networks when tested with XOR problems. Finally, in a comparative study of printed-letter categorization, the SD network model performed better than the traditional BP network.

A simple yet biologically plausible neuronal architecture that can account for the phenomenon of lightness constancy is explored. The model uses a hierarchical structure of overlapping operators at multiple levels of resolution. All operators have receptive fields organized concentrically into two antagonistic zones of center and surround. This C/S organization allows the computing structure to adaptively adjust the thresholds without prior knowledge of the intensity distribution. The principal idea here is to have larger operators set the thresholds for smaller ones. Local and global averages are used to shift IR curves. The architecture is based on the simple principles of convergence, divergence, and inhibition. The result is a computationally robust, regular structure, which can simplify implementation in VLSI.>