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. >

A software environment for studying computational neural systems

The sequential processing paradigm limits current solutions for computer vision by restricting the number of functions which naturally map onto Von Neumann computing architectures. A variety of physical computing structures underlie the massive parallelism inherent in many visual functions. Therefore, further advances in general purpose vision must assume inseparability of function from structure. To combine function and structure we are investigating connectionist architectures using PUNNS (Perception Using Neural Network Simulation). Our approach is inspired and constrained by the analysis of visual functions that are computed in the neural networks of living things. PUNNS represents a massively parallel computer architecture which is evolving to allow the execution of certain visual functions in constant time, regardless of the size and complexity of the image. Due to the complexity and cost of building a neural net machine, a flexible neural net simulator is needed to invent, study and understand the behavior of complex vision algorithms. Some of the issues involved in building a simulator are how to compactly describe the interconnectivity of the neural network, how to input image data, how to program the neural network, and how to display the results of the network. This paper describes the implementation of PUNNS. Simulation examples and a comparison of PUNNS to other neural net simulators will be presented.

UCLA PUNNS --A Neural Network Machine For Computer Vision

SFINX, a simulation environment for modeling a wide spectrum of neural architectures with both regular and irregular connectivity patterns, is discussed. SFINX is not based on a specific neural paradigm; it supports a variety of computational models ranging from simple convolution filters such as difference-of-Gaussians receptive fields used in image processing to learning paradigms such as backward error propagation. SFINX's main components and data are described, and the representation of explicit and implicit networks is examined. An explicit network is a collection of data structures that contain information about each node in the network. The name implicit networks reflects the fact that a node's activation value, output value, etc., are all distributed across a set of buffer array data structures and that the connectivity information is stored inside the node function. A simulation example is given to illustrate the use of SFINX. >

A tool for simulating neural models

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.

Lightness constancy from luminance contrast

Current interest in neural networks has produced a diverse set of algorithms and architectures that vary in connectivity pattern, temporal behavior, update rules, and convergence properties. We have designed a flexible simulation system that can support the implementation of a wide range of neural network approaches. The UCLA-SFINX simulator is especially suited for the exploration of structured, irregular, and layered connectivity patterns. Func tions, such as those in early vision, are modeled using the regular connectivity of center/surround antagonistic receptive fields and can be implemented as the difference of concentric gaussians. Higher level cognitive functions, such as supervised and unsuper vised learning, have more irregular, dynamic connectivity structures and update mechanisms that are also supported. To visualize weight spaces, input/output training sets, image data, or other network characteristics, SFINX provides an X- windows based graphical output that assists in rapidly assessing the ...

A general purpose simulation environment for neural models

Autonomous mobile robots must be capable of real-time recognition of moving objects in a time-varying scene. The motion of rigid objects can be analyzed in terms of edge features undergo-ing translation and rotation in the two-dimensional image. These features could be manipulated to match a fixed 3-D model. However, in a goal-driven system, where a priori knowledge of the 3-D model exists, it is more natural to manipulate the model before matching it to the edge features. We could speed up the 3-D to 2-D matching process by precomputing a range of possible orientations for the 3-D model. The difficulty is that one cannot predict all of the possible global changes of an object as it is moving in the scene. Our solution is to constrain the problem by looking at local changes that result from moving edge-features. The concept is borrowed from natural vision, where the visual field is divided into small regions and each region is analyzed by a column of orientation sensitive line segment operators. Each orientation operator has a preset maximal sensitivity to lines of a specific angle. Initially we assume that the 3-D model of a moving object has already been given. As an object rotates in the scene, the result is a spatial sequence of edges that activates adjacent columns. Heuristics to speed-up the matching of a 3-D model to a rotating or translating object can be derived from the local communication between neighboring columns of the moving edge features. The distance between successively activated columns can be used to measure how smoothly the edge features are undergoing motion. A slow moving object will produce a response in only a few successively adjacent columns and be interpreted as stepping slowly across the scene. A rapidly translating or rotating object will activate widely separated columns and be processed as undergoing discontinuous jumps. Similarly, in humans, when the velocity of key features in the visual field are either too low or too high, objects are perceived to be jumping instead of undergoing smooth motion [1].

David Gungner

Papers

UCLA PUNNS --A Neural Network Machine For Computer Vision

Lightness constancy from luminance contrast

A Connectionist Architecture For Matching 3-D Models To Moving Edge Features