Performance evaluation of a sequential minimal radial basisfunction (RBF) neural network learning algorithm

Presents a detailed performance analysis of the minimal resource allocation network (M-RAN) learning algorithm, M-RAN is a sequential learning radial basis function neural network which combines the growth criterion of the resource allocating network (RAN) of Platt (1991) with a pruning strategy based on the relative contribution of each hidden unit to the overall network output. The resulting network leads toward a minimal topology for the RAN. The performance of this algorithm is compared with the multilayer feedforward networks (MFNs) trained with 1) a variant of the standard backpropagation algorithm, known as RPROP and 2) the dependence identification (DI) algorithm of Moody and Antsaklis (1996) on several benchmark problems in the function approximation and pattern classification areas. For all these problems, the M-RAN algorithm is shown to realize networks with far fewer hidden neurons with better or same approximation/classification accuracy. Further, the time taken for learning (training) is also considerably shorter as M-RAN does not require repeated presentation of the training data.     

Communication channel equalization using complex-valued minimalradial basis function neural networks

A complex radial basis function neural network is proposed for equalization of quadrature amplitude modulation (QAM) signals in communication channels. The network utilizes a sequential learning algorithm referred to as complex minimal resource allocation network (CMRAN) and is an extension of the MRAN algorithm originally developed for online learning in real-valued radial basis function (RBF) networks. CMRAN has the ability to grow and prune the (complex) RBF network's hidden neurons to ensure a parsimonious network structure. The performance of the CMRAN equalizer for nonlinear channel equalization problems has been evaluated by comparing it with the functional link artificial neural network (FLANN) equalizer of J.C. Patra et al. (1999) and the Gaussian stochastic gradient (SG) RBF equalizer of I. Cha and S. Kassam (1995). The results clearly show that CMRANs performance is superior in terms of symbol error rates and network complexity.     

Measurement of fracture properties of Zr-2.5 Wt.% Nb pressure tube material and effect of trace impurities

This paper reports the details of a test method that uses elements of elastic-plastic fracture mechanics to assess fracture resistance of zirconium (Zr)-2.5 wt.% niobium (Nb) pressure tubes for a pressurized heavy water reactor. The fracture properties were evaluated on curved specimens, and the effect of certain trace elements on the fracture properties was determined. Significant reduction of trace impurities, produced by using four-stage melting practices rather than the conventional two-stage process, was observed to cause considerable improvement in the fracture resistance of the alloy. Scanning electron microscopy (SEM) of the fracture surfaces of the test specimens confirmed this observation.     

Comparison of two adaptive controllers

We are developing a simulation program to compare the performance of adaptive-control algorithms. Preliminary results indicate that a neutral control which includes caution, but not probing, is superior to the self-tuning regulator which includes neither.     

Parallel implementation of backpropagation neural networks on aheterogeneous array of transputers

This paper analyzes parallel implementation of the backpropagation training algorithm on a heterogeneous transputer network (i.e., transputers of different speed and memory) connected in a pipelined ring topology. Training-set parallelism is employed as the parallelizing paradigm for the backpropagation algorithm. It is shown through analysis that finding the optimal allocation of the training patterns amongst the processors to minimize the time for a training epoch is a mixed integer programming problem. Using mixed integer programming optimal pattern allocations for heterogeneous processor networks having a mixture of T805-20 (20 MHz) and T805-25 (25 MHz) transputers are theoretically found for two benchmark problems. The time for an epoch corresponding to the optimal pattern allocations is then obtained experimentally for the benchmark problems from the T805-20, TS805-25 heterogeneous networks. A Monte Carlo simulation study is carried out to statistically verify the optimality of the epoch time obtained from the mixed integer programming based allocations. In this study pattern allocations are randomly generated and the corresponding time for an epoch is experimentally obtained from the heterogeneous network. The mean and standard deviation for the epoch times from the random allocations are then compared with the optimal epoch time. The results show the optimal epoch time to be always lower than the mean epoch times by more than three standard deviations (3sigma) for all the sample sizes used in the study thus giving validity to the theoretical analysis.     

Nonlinear magnetic storage channel equalization using minimalresource allocation network (MRAN)

This letter presents the application of the recently developed minimal radial basis function neural network called minimal resource allocation network (MRAN) for equalization in highly nonlinear magnetic data storage channels. Using a realistic magnetic channel model, MRAN equalizer's performance is compared with the nonlinear neural equalizer of Nair and Moon (1997), referred to as maximum signal-to-distortion ratio (MSDR) equalizer. MSDR equalizer uses a specially designed neural architecture where all the parameters are determined theoretically. Simulation results indicate that MRAN equalizer has better performance than that of MSDR equalizer in terms of higher signal-to-distortion ratios.     

A Direct Link Minimal Resource Allocation Network for Adaptive Noise Cancellation

This paper presents a modification to the Minimal Resource Allocation Network (MRAN) of Yingwei et al. by introducing direct links from inputs to output and investigates its performance for noise cancellation problems. MRAN has the same structure as a Radial Basis Function network but uses a sequential learning algorithm that adds and prunes hidden neurons as input data is received sequentially so as to produce a parsimonious network. Earlier work by Sun Yonghong et al. has demonstrated the capability of MRAN to produce a compact network with excellent noise reduction properties. In this paper the capability of the direct link Minimal Resource Allocation Network (DMRAN) is evaluated by comparing it with MRAN on several nonlinear adaptive noise cancellation problems. The direct link MRAN uses the same learning algorithm as MRAN but with the introduction of direct links we are able to realise even smaller networks than MRAN with better noise reduction properties.     

Risk-sensitive loss functions for sparse multi-category classification problems

In this paper, we propose two risk-sensitive loss functions to solve the multi-category classification problems where the number of training samples is small and/or there is a high imbalance in the number of samples per class. Such problems are common in the bio-informatics/medical diagnosis areas. The most commonly used loss functions in the literature do not perform well in these problems as they minimize only the approximation error and neglect the estimation error due to imbalance in the training set. The proposed risk-sensitive loss functions minimize both the approximation and estimation error. We present an error analysis for the risk-sensitive loss functions along with other well known loss functions. Using a neural architecture, classifiers incorporating these risk-sensitive loss functions have been developed and their performance evaluated for two real world multi-class classification problems, viz., a satellite image classification problem and a micro-array gene expression based cancer classification problem. To study the effectiveness of the proposed loss functions, we have deliberately imbalanced the training samples in the satellite image problem and compared the performance of our neural classifiers with those developed using other well-known loss functions. The results indicate the superior performance of the neural classifier using the proposed loss functions both in terms of the overall and per class classification accuracy. Performance comparisons have also been carried out on a number of benchmark problems where the data is normal i.e., not sparse or imbalanced. Results indicate similar or better performance of the proposed loss functions compared to the well-known loss functions.     

Microstructure evolution and tensile properties of Zr-2.5wt%Nb pressure tubes processed from billets with different microstructures

Starting with identical ingots, billets having different microstructures were obtained by three different processing methods for fabrication of Zr-2.5wt%Nb pressure tubes. The billets were further processed by hot extrusion and cold Pilger tube reducing to the finished product. Microstructural characterization was done at each stage of processing. The effects of the initial billet microstructure on the intermediate and final microstructure and mechanical property results were determined. It was found that the structure at each stage and the final mechanical properties depend strongly on the initial billet microstructure. The structure at the final stage consists of elongated alpha zirconium grains with a network of metastable beta zirconium phase. Some of this metastable phase transforms into stable beta niobium during thermomechanical processing. Billets with quenched structure resulted in less beta niobium at the final stage. The air cooled billets resulted in a large amount of beta niobium. The tensile properties, especially the percentage elongation, were found to vary for the different methods. Higher percentage elongation was observed for billets having quenched structure. Extrusion and forging did not produce any characteristic differences in the properties. The results were used to select a process flow sheet which yields the desired mechanical properties with suitable microstructure in the final product.     

Comparison of adaptive controllers

The paper investigates adaptive control of discrete-time processes satisfying first-order linear difference equations with random coefficients which may be constant or time-varying. Structural relationships between sub-optimal adaptive control laws are discussed and results of systematic Monte-Carlo simulations are reported. These lead to a comparison of two sub-optimal adaptive controls ($\text{‘}\text{optimal}\text{-k-}\text{step-ahead}$’ and ‘self-tuning’) and to conclusions about the need for and effectiveness of adaptive control of the systems simulated. It is conjectured that the results and the classification scheme they suggest might have more general validity.