International Journal of Neural Systems

This paper presents one possible implementation of a transformation that performs linear mapping to a lower-dimensional subspace. Principal component subspace will be the one that will be analyzed. Idea implemented in this paper represents generalization of the recently proposed ∞OH neural method for principal component extraction. The calculations in the newly proposed method are performed locally — a feature which is usually considered as desirable from the biological point of view. Comparing to some other wellknown methods, proposed synaptic efficacy learning rule requires less information about the value of the other efficacies to make single efficacy modification. Synaptic efficacies are modified by implementation of Modulated Hebb-type (MH) learning rule. Slightly modified MH algorithm named Modulated Hebb Oja (MHO) algorithm, will be also introduced. Structural similarity of the proposed network with part of the retinal circuit will be presented, too.

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.

This paper presents a novel approach to the correction of panoramic (wide-angle) image distortions. Unlike traditional methods that separate the distortion of the panoramic image into radial and tangential components and then concentrate on the correction of one type of distortion at a time, the method presented in this paper uses an integrated approach that simultaneously corrects all non-linear distortions of the panoramic image. The system uses data obtained from carefully constructed calibration patterns to automatically build and train a constructive neural network of suitable complexity to approximate the characteristic distortion of the panoramic image. The trained neural network is then used to correct the distortions represented by the sample data. It is demonstrated that by applying the distortion correction method presented in this paper to panoramic images representing real world scenes, perspective-corrected views of the real world scene that are usable in a wide variety of applications can be generated.

This paper presents a novel Call Admission Control (CAC) scheme which adopts the neural network approach, namely Minimal Resource Allocation Network (MRAN) and its extended version EMRAN. Though the current focus is on the Call Admission Control (CAC) for Asynchronous Transfer Mode (ATM) networks, the scheme is applicable to most high-speed networks. As there is a need for accurate estimation of the required bandwidth for different services, the proposed scheme can offer a simple design procedure and provide a better control in fulfilling the Quality of Service (QoS) requirements. MRAN and EMRAN are on-line learning algorithms to facilitate efficient admission control in different traffic environments. Simulation results show that the proposed CAC schemes are more efficient than the two conventional CAC approaches, the Peak Bandwidth Allocation scheme and the Cell Loss Ratio (CLR) upperbound formula scheme. The prediction precision and computational time of MRAN and EMRAN algorithms are also investigated. Both MRAN and EMRAN algorithms yield similar performance results, but the EMRAN algorithm has less computational load.

An efficient method for fingerprint searching using recurrent autoassociative memory is proposed. This algorithm uses recurrent autoassociative memory, which uses a connectivity matrix to find if the pattern being searched is already stored in the database. The advantage of this memory is that a big database is to be searched only if there is a matching pattern. Fingerprint comparison is usually based on minutiae matching, and its efficiency depends on the extraction of minutiae. This process may reduce the speed, when large amount of data is involved. So, in the proposed method, a simple approach has been adopted, wherein first determines the closely matched fingerprint images, and then determines the minutiae of only those images for finding the more appropriate one. The gray level value of pixels along with its neighboring ones are considered for the extraction of minutiae, which is more easier than using ridge information. This approach is best suitable when database size is large.