Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

Neural networks

Discipline
Institution
Publication Year
Publication
Publication Type
File Type

Articles 331 - 345 of 345

Full-Text Articles in Computer Sciences

Performance Modeling Of Load Balancing Algorithms Using Neural Networks, Ishfaq Ahmad, Arif Ghafoor, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka Jan 1994

Performance Modeling Of Load Balancing Algorithms Using Neural Networks, Ishfaq Ahmad, Arif Ghafoor, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

College of Engineering and Computer Science - Former Departments, Centers, Institutes and Projects

This paper presents a new approach that uses neural networks to predict the performance of a number of dynamic decentralized load balancing strategies. A distributed multicomputer system using any distributed load balancing strategy is represented by a unified analytical queuing model. A large simulation data set is used to train a neural network using the back–propagation learning algorithm based on gradient descent. The performance model using the predicted data from the neural network produces the average response time of various load balancing algorithms under various system parameters. The validation and comparison with simulation data show that the neural network is …

Go to article

Applications Of Fuzzy Counterpropagation Neural Networks To Non-Linear Function Approximation And Background Noise Elimination, I. M. Wiryana Jan 1994

Applications Of Fuzzy Counterpropagation Neural Networks To Non-Linear Function Approximation And Background Noise Elimination, I. M. Wiryana

Theses: Doctorates and Masters

An adaptive filter which can operate in an unknown environment by performing a learning mechanism that is suitable for the speech enhancement process. This research develops a novel ANN model which incorporates the fuzzy set approach and which can perform a non-linear function approximation. The model is used as the basic structure of an adaptive filter. The learning capability of ANN is expected to be able to reduce the development time and cost of the designing adaptive filters based on fuzzy set approach. A combination of both techniques may result in a learnable system that can tackle the vagueness problem …

Go to article

A Model Of Visual Recognition Implemented Using Neural Networks, Vincent C. Phillips Jan 1994

A Model Of Visual Recognition Implemented Using Neural Networks, Vincent C. Phillips

Theses: Doctorates and Masters

The ability to recognise and classify objects in the environment is an important property of biological vision. It is highly desirable that artificial vision systems also have this ability. This thesis documents research into the use of artificial neural networks to implement a prototype model of visual object recognition. The prototype model, describing a computtional architecture, is derived from relevant physiological and psychological data, and attempts to resolve the use of structural decomposition and invariant feature detection. To validate the research a partial implementation of the model has been constructed using multiple neural networks. A linear feed-forward network performs pre-procesing …

Go to article

Recurrent Neural Networks For Radar Target Identification, Eric T. Kouba Dec 1992

Recurrent Neural Networks For Radar Target Identification, Eric T. Kouba

Theses and Dissertations

A real-time recurrent learning algorithm was applied to a five class radar target identification problem. The wideband radar was assumed to measure both kinematic (tracking information expressed as estimated aspect angles) and high range resolution data from a single, isolated aircraft. The aspect angles (azimuth and elevation) of the aircraft relative to the radar were assumed to be constantly chancing. This created temporal sequences of high range resolution radar signatures that changed as the aspect angles changed. These sequences were used as input features to a recurrent neural network for three radar target identification test cases. The first test case …

Go to article

Text-Independent Automatic Speaker Identification Using Partitioned Neural Networks, Laszlo Rudasi Jul 1992

Text-Independent Automatic Speaker Identification Using Partitioned Neural Networks, Laszlo Rudasi

Electrical & Computer Engineering Theses & Dissertations

This dissertation introduces a binary partitioned approach to statistical pattern classification which is applied to talker identification using neural networks. In recent years artificial neural networks have been shown to work exceptionally well for small but difficult pattern classification tasks. However, their application to large tasks (i.e., having more than ten to 20 categories) is limited by a dramatic increase in required training time. The time required to train a single network to perform N-way classification is nearly proportional to the exponential of N. In contrast, the binary partitioned approach requires training times on the order of N2. …

Go to article

Bounds On Constraint Weight Parameters Of Hopfield Networks For Stability Of Optimization Problem Solutions, Gursel Serpen Jan 1992

Bounds On Constraint Weight Parameters Of Hopfield Networks For Stability Of Optimization Problem Solutions, Gursel Serpen

Electrical & Computer Engineering Theses & Dissertations

The purpose of the presented research is to study the convergence characteristics of Hopfield network dynamics. The relation between constraint weight parameter values and the stability of solutions of constraint satisfaction and optimization problems mapped to Hopfield networks is investigated. A theoretical development relating constraint weight parameter values to solution stability is presented. The dependency of solution stability on constraint weight parameter values is shown employing an abstract optimization problem. A theorem defining bounds on the constraint weight parameter magnitudes for solution stability of constraint satisfaction and optimization problems is proved. Simulation analysis on a set of optimization and constraint …

Go to article

A Comparison Of Load Balancing Algorithms For Parallel Computations, N. Mansouri, Geoffrey C. Fox Sep 1991

A Comparison Of Load Balancing Algorithms For Parallel Computations, N. Mansouri, Geoffrey C. Fox

Electrical Engineering and Computer Science - Technical Reports

Three physical optimization methods are considered in this paper for load balancing parallel computations. These are simulated annealing, genetic algorithms, and neural networks. Some design choices and the inclusion of additional steps lead to new versions of the algorithms with different solution qualities and execution times. The performances of these versions are critically evaluated and compared for test cases with different topologies and sizes. Orthogonal recursive coordinate bisection is also included in the comparison as a typical simple deterministic method. Simulation results show that the algorithms have diverse properties. Hence, different algorithms can be applied to different problems and requirements. …

Go to article

An Improved Algorithm For Neural Network Classification Of Imbalanced Training Sets, Rangachari Anand, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka Aug 1991

An Improved Algorithm For Neural Network Classification Of Imbalanced Training Sets, Rangachari Anand, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Electrical Engineering and Computer Science - Technical Reports

In this paper, we analyze the reason for the slow rate of convergence of net output error when using the backpropagation algorithm to train neural networks for a two-class problems in which the numbers of exemplars for the two classes differ greatly. This occurs because the negative gradient vector computed by backpropagation for an imbalanced training set does not point initially in a downhill direction for the class with the smaller number of exemplars. Consequently, in the initial iteration, the net error for the exemplars in this class increases significantly. The subsequent rate of convergence of the net error is …

Go to article

Connectionist Expert System With Adaptive Learning Capability, B. T. Low, Hochung Lui, Ah-Hwee Tan, Hoonheng Teh Jun 1991

Connectionist Expert System With Adaptive Learning Capability, B. T. Low, Hochung Lui, Ah-Hwee Tan, Hoonheng Teh

Research Collection School Of Computing and Information Systems

A neural network expert system called adaptive connectionist expert system (ACES) which will learn adaptively from past experience is described. ACES is based on the neural logic network, which is capable of doing both pattern processing and logical inferencing. The authors discuss two strategies, pattern matching ACES and rule inferencing ACES. The pattern matching ACES makes use of past examples to construct its neural logic network and fine-tunes itself adaptively during its use by further examples supplied. The rule inferencing ACES conceptualizes new rules based on the frequencies of use on the rule-based neural logic network. A new rule could …

Go to article

Analyzing Images Containing Multiple Sparse Patterns With Neural Networks, Rangachari Anand, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka Jan 1991

Analyzing Images Containing Multiple Sparse Patterns With Neural Networks, Rangachari Anand, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

College of Engineering and Computer Science - Former Departments, Centers, Institutes and Projects

We have addressed the problem of analyzing images containing multiple sparse overlapped patterns. This problem arises naturally when analyzing the composition of organic macromolecules using data gathered from their NMR spectra. Using a neural network approach, we have obtained excellent results in using NMR data to analyze the presence of various amino acids in protein molecules. We have achieved high correct classification percentages (about 87%) for images containing as many as five substantially distorted overlapping patterns.

Go to article

An Examination And Analysis Of The Boltzmann Machine, Its Mean Field Theory Approximation, And Learning Algorithm, Vincent Clive Phillips Jan 1991

An Examination And Analysis Of The Boltzmann Machine, Its Mean Field Theory Approximation, And Learning Algorithm, Vincent Clive Phillips

Theses : Honours

It is currently believed that artificial neural network models may form the basis for inte1ligent computational devices. The Boltzmann Machine belongs to the class of recursive artificial neural networks and uses a supervised learning algorithm to learn the mapping between input vectors and desired outputs. This study examines the parameters that influence the performance of the Boltzmann Machine learning algorithm. Improving the performance of the algorithm through the use of a naïve mean field theory approximation is also examined. The study was initiated to examine the hypothesis that the Boltzmann Machine learning algorithm, when used with the mean field approximation, …

Go to article

Forecasting The Behavior Of Multivariate Time Series Using Neural Networks, Kanad Charkraborty, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka Nov 1990

Forecasting The Behavior Of Multivariate Time Series Using Neural Networks, Kanad Charkraborty, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Electrical Engineering and Computer Science - Technical Reports

This paper presents a neural network approach to multivariate time-series analysis. Real world observations of flour prices in three cities have been used as a benchmark in our experiments. Feedforward connectionist networks have been designed to model flour prices over the period from August 1972 to November 1980 for the cities of Buffalo, Minneapolis, and Kansas City. Remarkable success has been achieved in training the networks to learn the price curve for each of these cities, and thereby to make accurate price predictions. Our results show that the neural network approach leads to better predictions than the autoregressive moving average(ARMA) …

Go to article

Korean Character Recognition Using Neural Networks, Jinhwan Koh, G. S. Moon, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka May 1990

Korean Character Recognition Using Neural Networks, Jinhwan Koh, G. S. Moon, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Electrical Engineering and Computer Science - Technical Reports

We present a neural-network approach for recognizing printed Korean characters. Our approach is based on a variant of the back-propagation algorithm. The results indicate that by transforming the character data into Hough space, we can achieve excellent recognition.

Go to article

A Neural Network Simulator For The Connnection Machine, N. Asokan, Ravi V. Shankar, Chilukuri K. Mohan, Kishan Mehrotra, Sanjay Ranka May 1990

A Neural Network Simulator For The Connnection Machine, N. Asokan, Ravi V. Shankar, Chilukuri K. Mohan, Kishan Mehrotra, Sanjay Ranka

Electrical Engineering and Computer Science - Technical Reports

In this paper we describe the design, development, and performance of a neural network simulator for the Connection Machine (CM)3. The design of the simulator is based on the Rochester Connectionist Simulator(RCS). RCS is a simulator for connectionist networks developed at the University of Rochester. The CM simulator can be used as a stand-alone system or as a high-performance parallel back-end to RCS. In the latter case, once the network has been built by RCS, the high-performance parallel back-end system constructs an equivalent network on the CM processor array and executes it. The CM simulator facilitates the exploitation of the …

Go to article

Digital Neural Networks, Tony R. Martinez Jan 1988

Digital Neural Networks, Tony R. Martinez

Faculty Publications

Demands for applications requiring massive parallelism in symbolic environments have given rebirth to research in models labeled as neural networks. These models are made up of many simple nodes which are highly interconnected such that computation takes place as data flows amongst the nodes of the network. To present, most models have proposed nodes based on simple analog functions, where inputs are multiplied by weights and summed, the total then optionally being transformed by an arbitrary function at the node. Learning in these systems is accomplished by adjusting the weights on the input lines. This paper discusses the use of …

Go to article

First Prev