Search

A formal methodology drives the design and realization of a digital very large-scale integration (VLSI) device supporting hierarchical vector quantization (HVQ) in computation-intensive coding applications. The hardware-oriented model-selection approach enhances the Minimum Description Length criterion with circuit-related aspects that allow consistent and efficient design. The resulting model parameters drive the subsequent realization in digital circuitry, which has first been implemented in field-programmable gate array (FPGA) technology to verify its correctness. The eventual VLSI realization results in an HVQ chip providing cost-effective, computationally efficient real-time performances. Real-world applications support the consistency of the vector quantization approach and the effectiveness of the HVQ device. Index Terms--Digital very large-scale integration (VLSI), minimum description length (MDL), vector quantization (VQ).

The increasing use of compression standards in broadcasting digital TV has raised the need for established criteria to measure perceived quality. Novel methods must take into account the specific artifacts introduced by digital compression techniques. This paper presents a methodology using circular backpropagation (CBP) neural networks for the objective quality assessment of motion picture expert group (MPEG) video streams. Objective features are continuously extracted from compressed video streams on a frame-by-frame basis; they feed the CBP network estimating the corresponding perceived quality. The resulting adaptive modeling of subjective perception supports a real-time system for monitoring displayed video quality. The overall system mimics perception but does not require an analytical model of the underlying physical phenomenon. The ability to process compressed video streams represents a crucial advantage over existing approaches, as avoiding the decoding process greatly enhances the system's real-time performance. Experimental evidence confirmed the approach validity. The system was tested on real test videos; they included different contents ranging from fiction to sport. The neural model provided a satisfactory, continuous-time approximation for actual scoring curves, which was validated statistically in terms of confidence analysis. As expected, videos with slow-varying contents such as fiction featured the best performances. Index Terms--Circular backpropagation (CBP), compressed video, digital TV, objective quality assessment.

The design and prototypal realization of a visual tracking system is presented. The approach to target identification is nonconventional, in that it relies on an architecture composed of multiple standard neural networks (multilayer perceptrons) and exploits the information contained in simple features extracted from images, performing a small number of operations. Therefore, the tracking functions are learned by examples, rather than implemented directly. The system demonstrates that a quite complex task such as visual target tracking can be easily obtained by a suitable neural architecture. The fast tracking algorithm and the parallel structure allow a true real-time operation. The system exploits a two-level neural-network hierarchy with a number of parallel networks and an 'arbiter.' The training set consists of various geometrical shapes, preprocessed to yield the data vectors. The experimental hardware implementation is based on multiple processing units, implementing the neural architecture, and serves as a prototype for the analysis of the system in practice. A small-sized realization can also be obtained. Index Terms - Machine vision, multilayer perceptrons, multiprocessing, neural network applications, neurocontrollers, tracking.

This letter proves the equivalence between vector quantization (VQ) classifiers and circular backpropagation (CBP) networks. The calibrated prototypes for a VQ schema can be plugged in a CBP feedforward structure having the same number of hidden neurons and featuring the same mapping. The letter describes how to exploit such equivalence by using VQ prototypes to perform a meaningful initialization for BP optimization. The approach effectiveness was tested considering a real classification problem (NIST handwritten digits). Index Terms - Feedforward neural networks, optical character recognition, vector quantization.

The class of mapping networks is a general family of tools to perform a wide variety of tasks; however, no unifying framework exists to describe their theoretical and practical properties. This paper presents a standardized, uniform representation for this class of networks, and introduces a simple modification of the multilayer perceptron with interesting practical properties, especially well suited to cope with pattern classification tasks. The proposed model unifies the two main representation paradigms found in the class of mapping networks for classification, namely, the surface-based and the prototype-based schemes, while retaining the advantage of being trainable by backpropagation. The enhancement in the representation properties and the generalization performance are assessed through results about the worst-case requirement in terms of hidden units and about the Vapnik-Chervonenkis dimension and Cover capacity. The theoretical properties of the network also suggest that the proposed modification to the multilayer perceptron is in many senses optimal. A number of experimental verifications also confirm theoretical results about the model's increased performances, as compared with the multilayer perceptron and the Gaussian radial basis functions network. Index Terms - Feedforward neural networks, backpropagation, pattern classification, knowledge representation

This paper describes a distributed method for traffic control and addresses the crucial problem of stability from both a formal and a practical perspective. Within a continuous-time and continuous-space approximation, a mathematical analysis first demonstrates the inherent stability of priority-based local decision making. Then, a more realistic model takes into account a network's finite connectivity and the time-discrete nature of events. This paper shows how deadlock-avoidance algorithms can be effectively included in a distributed system. Experimental results obtained by a realistic railway model prove that the inclusion of deadlock avoidance can provide early detection of critical situations, thus making it possible to schedule appropriate decisions or to drive a routing mechanism to enhance traffic flow.