The design of artificial neural networks (ANNs) through simulated evolution has been investigated for many years. The use of genetic algorithms (GAs) for such evolution suffers a prominent problem known as the permutation problem or the competing convention problem. This paper proposes a new crossover operator, which we call the selected node crossover (SNX), to overcome the permutation problem of GAs for evolving ANNs. A GA-based evolutionary system (GANet) using the SNX for evolving three layered feedforward ANNs architecture with weight learning is described. GANet uses one crossover and one mutation operators sequentially. If the first operator is successful then the second operator is not applied. GANet is less dependent on user-defined control parameters than the conventional evolutionary methods. GANet is applied to a variety of benchmarks including large (26 class) to small (2 class) classification problems. The results show that GANet can produce compact ANN architectures with small classification errors.

Feature selection is an integral part of any pattern recognition system. Removal of redundant features improves the efficiency of a classifier as well as cut down the cost of future feature extraction. Recently neural network classifiers have become extremely popular compared to their counterparts from statistical theory. Some works on the use of artificial neural network as a feature selector have already been reported. In this work a simple feature selection algorithm has been proposed in which a fractal neural network, a modified version of multilayer perceptron, has been used as a feature selector. Experiments have been done with IRIS and SONAR data set by simulation. Results suggest that the algorithm with the fractal network architecture works well for removal of redundant informations as tested by classification rate. The fractal neural network takes lesser training time than the conventional multilayer perceptron for its lower connectivity while its performance is comparable to the multilayer perceptron. The ease of hardware implementation is also an attractive point in designing feature selector with fractal neural network.

In this paper CMOS VLSI circuit solutions are suggested for on-chip learning and weight storage, which are simple and silicon area efficient. In particular a stochastic learning scheme, named Random Weight Change, and a multistable weight storage approach have been implemented. Additionally, the problems of the influence of technological variations on learning accuracy is discussed. Even though both the learning scheme and the weight storage are quite general, in the paper we will refer to a class of networks, named Approximate Identity Neural Networks, which are particularly suitable to be implemented with analog CMOS circuits. As a test vehicle a small network with four neurons, 16 weights, on chip learning and weight storage has been fabricated in a 1.2 µm double-metal CMOS process.

This paper describes a new Artificial Neural Network (ANN), UNItary Decomposition ANN (UNIDANN), which can perform the unitary eigendecomposition of the synaptic weight matrix. It is shown both analytically and quantitatively that if the synaptic weight matrix is Hermitian positive definite, the neural output, based on the proposed dynamic equation, will converge to the principal eigenvectors of the synaptic weight matrix. Compared with previous works, the UNIDANN possesses several advantageous features such as low computation time and no synchronization problem due to the underlying analog circuit structure, faster convergence speed, accurate final results, and numerical stability. Some simulations with a particular emphasis on the applications to high resolution bearing estimation problems are also furnished to justify the proposed ANN.

In the present communication we propose the application of unsupervised Artificial Neural Networks (ANN) to solve general ill-posed problems and particularly we apply them to the the estimation of the direction of arrival (DOA) of VLF/ELF radio waves. We use the wave distribution method which consists in the reconstruction of the energy distribution of magnetospheric VLF/ELF waves at the ionospheric base from observations of the wave's electromagnetic field on the ground. The present application is similar to a number of computerized tomography and image enhancement problems and the proposed algorithm can be straightforwardly extended to other applications in which observations are linearly related to unknowns. Then, we have proven the applicability and also we indicate the superiority of the ANN to the conventional methods to handle this kind of problems.

In this paper, we present some contributions to improve a previous work's approach presented for the segmentation of magnetic resonance images of the human brain, based on the unsupervised Hopfield neural network. We formulate the segmentation problem as a minimization of an energy function constructed with two terms, the cost-term as a sum of errors' squares, and the second term is a temporary noise added to the cost-term as an excitation to the network to escape from certain local minimums and be more close to the global minimum. Also, to ensure the convergence of the network and its utility in clinic with useful results, the minimization is achieved with a step function permitting the network to reach its stability corresponding to a local minimum close to the global minimum in a prespecified period of time. We present here our approach segmentations results of a patient data diagnosed with a metastatic tumor in the brain, and we compare them to those obtained based on, previous works using Hopfield neural networks, Boltzmann machine and the conventional ISODATA clustering technique.

A novel algorithm, as an advanced Hybrid Channel Assignment strategy, for channel assignment problem in a cellular system is proposed. A difference from the conventional Hybrid Channel Assignment method is that flexible fixed channel allocations which are variable through the channel assignment can be performed in order to cope with varying traffic. This strategy utilizes the Channel Rearrangement technique using the artificial neural network algorithm in order to enhance channel occupancy on the fixed channels. The strategy is applied to two simulation models which are the spatial homogeneous and inhomogeneous systems in traffic. The simulation results show that the strategy can effectively improve blocking probability in comparison with pure dynamic channel assignment strategy only with the Channel Rearrangement.

We apply neural networks to implement a line shape recognition/classification system. The purpose of employing neural networks is to eliminate target-specific algorithms from the system and to simplify the system. The system needs only to be trained by samples. The shapes are captured by the following operations. Lines to be processed are segmented at inflection points. Each segment is extended from both ends of it in a certain percentage. The shape of each extended segment is captured as an approximate curvature. Curvature sequence is normalized by size in order to get a scale-invariant measure. Feeding this normalized curvature date to a neural network leads to position-, rotation-, and scale-invariant line shape recognition. According to our experiments, almost 100% recognition rates are achieved against 5% random modification and 50%-200% scaling. The experimental results show that our method is effective. In addition, since this method captures shape locally, partial lines (caused by overlapping etc.) can also be recognized.

In cellular mobile systems, an alternative approach for a Dynamic Channel Assignment problem is presented. It adaptively assigns the channels considering the cochannel interference level. The Dynamic Channel Assignment problem is modeled on the different cellular system from the conventional one. In this paper, we formulate the rearrangement problem in the Dynamic Channel Assignment and propose a novel strategy for the problem. The proposed algorithm is based on an artificial neural network as a specific dynamical system, and is successfully applied to the cellular system models. The computer simulation results show that the algorithm utilized for the rearrangement is an effective strategy to improve the traffic characteristics.

We present an extension of the previously proposed 3-layer feedforward network called a cascaded network. Cascaded networks are trained to realize category classification employing binary input vectors and locally represented binary target output vectors. To realize a nonlinearly separable task the extended cascaded network presented here is consreucted by introducing high order cross producted inputs at the input layer. In the construction of the cascaded network, two 2-layer networks are first trained independently by delta rule and then cascaded. After cascading, the intermediate layer can be understood as a hidden layer which is trained to attain preassigned saturated outputs in response to the training set. In a cascaded network trained to categorize binary image patterns, saturation of hidden outputs reduces the effect of corrupted disturbances presented in the input. We demonstrated that the extended cascaded network was able to realize a nonlinearly separable task and yielded better generalization ability than the Backpropagation network.

The recent non von Neumann chip architectures are mainly classified into the AI architecture and the neural architecture. We focus on these two categories, and introduce the representatives each with a brief history. The AI chip architecture is difficult to escape essentially from the von Neumann architecture as far as it is language-oriented. The neural architecture, however, may yield an essentially new computer architecture, when the new device technologies will support it. In particular, the optoelectronics and the quantum electronics will provide a lot of powerful technologies.

It has been reported that generalization performance of multilayer feedformard networks strongly depends on the attainment of saturated hidden outputs in response to the training set. Usually standard Backpropagation (BP) network mostly uses intermediate values of hidden units as the internal representation of the training patterns. In this letter, we propose construction of a 3-layer cascaded network in which two 2-layer networks are first trained independently by delta rule and then cascaded. After cascading, the intermediate layer can be viewed as hidden layer which is trained to attain preassigned saturated outputs in response to the training set. This network is particularly easier to construct for linearly separable training set, and can also be constructed for nonlinearly separable tasks by using higher order inputs at the input layer or by assigning proper codes at the intermediate layer which can be obtained from a trained Fahlman and Lebiere's network. Simulation results show that, at least, when the training set is linearly separable, use of the proposed cascaded network significantly enhances the generalization performance compared to BP network, and also maintains high generalization ability for nonlinearly separable training set. Performance of cascaded network depending on the preassigned codes at the intermediate layer is discussed and a suggestion about the preassigned coding is presented.