Abstract:
Given an undirected graph with weights on the vertices, the maximum weight clique problem (MWCP) is to find a subset of mutually adjacent vertices (i.e., a clique) having largest total weight. This is a generalization of the classical problem of finding the maximum cardinality clique of an unweighted graph, which arises as a special case of the MWCP when all the weights associated to the vertices are equal. The problem is known to be NP-hard for arbitrary graphs and, according to recent theoretical results, so is the problem of approximating it within a constant factor.

Although there has recently been much interest around neural network algorithms for the unweighted maximum clique problem, no effort has been directed so far towards its weighted counterpart. In this paper, we present a parallel, distributed heuristic for approximating the MWCP based on dynamics principles developed and studied in various branches of mathematical biology. The proposed framework centers around a recently introduced continuous characterization of the MWCP which generalizes an earlier remarkable result by Motzkin and Straus. This allows us to formulate the MWCP (a purely combinatorial problem) in terms of a continuous quadratic programming problem. One drawback associated with this formulation, however, is the presence of "spurious" solutions, and
we present characterizations of these solutions. To avoid them we introduce a new regularized continuous formulation of the MWCP inspired by previous works on the unweighted problem, and show how this approach completely solves the problem.

The continuous formulation of the MWCP naturally maps onto a parallel, distributed computational network whose dynamical behavior is governed by the so-called replicator equations. These are dynamical systems introduced in evolutionary game theory and population genetics to model evolutionary processes on a macroscopic scale. We present theoretical results which guarantee that the solutions provided by our clique finding replicator network are actually the ones being sought. Extensive experiments on both randomly generated and standard benchmark graphs have been conducted, and the results obtained confirm the effectiveness of the proposed approach.

A Multithreaded Approach to Real Time Face Tracking
http://mplab.ucsd.edu
Boris E. Shpungin and Javier R. Movellan

Abstract:
We present a multithreaded approach to real-time face tracking.  The system consists of a set of modules running on different processing threads and coordinated by a mini operating system. The first module uses color, shape, and face dynamics to determine a 2-D region of interest.  The second module is a mixture of linear experts classifier whose task is to help determine whether the region of interest is indeed a face.

Active Inference in Concept Induction
http://mplab.ucsd.edu
Jonathan D. Nelson and Javier R. Movellan

Abstract:
People are active information gatherers, constantly experimenting and seeking information relevant to their goals. A reasonable approach to active information gathering is to ask questions and conduct experiments that maximize the expected information gain given our current beliefs (Lindley, 1956; Good, 1966; MacKay, 1992). In this paper we compare the behavior of human subjects with that of an optimal information-gathering agent (infomax) in a concept induction task (Tennenbaum, 1999). Results show high consistency between subjects in their information gathering behavior. However infomax generally fails to
predict what subjects do. It is unclear at this point whether the failure of infomax is due to problems with  Tennenbaum's concept induction model, or due to the fact that subjects use suboptimal heuristics (e.g., confirmatory sampling).

Blind Signal Processing by the Adaptive Activation Function Neurons
Requests of copies should be addressed to: sfr@unipg.it
S. Fiori (University of Perugia, Perugia, Italy)

Abstract:
The aim of this paper is to study an Information-Theoretic based learning theory for neural units endowed with adaptive activation functions. The learning theory has the target to force the neuron to approximate the input-output transference that makes it flat (uniform) the probability density function of its output or, equivalently, that maximizes the entropy of the neuron response. Then, a network of adaptive activation function neurons is studied, and the effectiveness of the new structure is tested on independent component analysis (ICA) problems. The new ICA neural algorithm is compared with the closely-related `Mixture of Densities' (MOD) technique by Xu \emph{et al.}.

Weighted Least-Squares Blind Deconvolution of Non-Minimum Phase Systems
Requests of copies should be addressed to: sfr@unipg.it
S. Fiori (University of Perugia, Perugia, Italy); G. Maiolini (University of Ancona, Ancona, Italy)

Abstract:
We propose a new algorithm based on a weighted least-squares technique that allows on-line deconvolution of non-minimum phase systems with no knowledge of system's impulse response nor source statistics except for source signal moments up to the fourth order. Through computer simulations and computational  complexity evaluation, we illustrate and compare the performances and the features of the proposed method with those exhibited by other existing techniques found in the scientific literature.

Self-Organization of Topographic Mixture Networks Using Attentional Feedback
http://cns-web.bu.edu/pub/jrw/www/pubs.html
James R. Williamson (Boston University)

Abstract:
This paper proposes a neural network model of supervised learning which employs biologically-motivated constraints of using local, on-line, constructive learning.  The model possesses two novel learning mechanisms.  The first is a network for learning topographic mixtures.  The network's internal category nodes are the mixture components, which learn to encode smooth distributions in the input space by taking advantage of topography in the input feature maps.
The second mechanism is an attentional biasing feedback circuit. When the network makes an incorrect output prediction, this feedback circuit modulates the learning rates of the category nodes, by amounts based on the sharpness of their tuning, in order to improve the network's prediction accuracy.  The network is evaluated on several standard classification benchmarks and shown to perform well in comparison to other classifiers.

A Dual Route Cascaded Model of Visual Word Recognition and Reading Aloud
http://www.maccs.mq.edu.au/~max/DRC/
M. Coltheart, K. Rastle, C. Perry, R. Langdon, R. and J. Ziegler (Macquarie University, Australia)

Abstract:
In this paper we describe a computational model of visual word recognition and reading aloud, the Dual Route Cascaded (DRC) model, a computational realisation of the dual-route theory of reading. The two tasks most commonly used to study reading are lexical decision and reading aloud; the DRC model is the only computational model of reading which can perform both of these tasks. The model is evaluated by comparing its lexical decision latency data to lexical decision
latency data from various published studies of human subjects, and by comparing its reading aloud latency data to reading aloud latency data from various published studies of reading aloud by human subjects. For both tasks, it is found that a wide variety of variables which affect human latencies affect the DRC model's latencies in exactly the same way. We note a number of such effects which the DRC model simulates but which other computational models of reading do not, whereas as far as we are aware there are no effects which any other current computational model of reading can simulate but which the DRC model cannot. We conclude that the DRC model is the most successful of existing computational models of reading.

Using the electronic medical record to predict the pharmacological management of acute myocardial infarction
 by Abston, Karen Crowley, PhD
 THE UNIVERSITY OF UTAH, 1999, 94 pages

Decomposition strategies for process identification and control using neural networks
 by Adebiyi, Olufemi Adeniyi, PhD
 THE LOUISIANA STATE UNIVERSITY AND AGRICULTURAL AND MECHANICAL COL., 1999, 197 pages

Analysis of fetal heart rate variability and stress conditions in fetuses using wavelets and neural networks (ALOPEX): A feasibility study
 by Akay, Yasemin Munevver, PhD
 RUTGERS THE STATE U. OF N.J. - NEW BRUNSWICK AND U.M.D.N.J., 1999, 120 pages

Transmission expansion planning using artificial intelligent tools
 by Al-Saba, Tawfiq Taher, MS
 KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS (SAUDI ARABIA), 1999, 211 pages

Improving image classification accuracy by combining maximum likelihood classifier and artificial networks
 by Al-Shaikh, Ahmad Husain, PhD
 THE UNIVERSITY OF WISCONSIN - MADISON, 1999, 191 pages

Automated computer-brain feedback system for auditory stimulus optimization
 by Anderson, Michael John, Sr., PhD
 RUTGERS THE STATE UNIVERSITY OF NEW JERSEY - NEW BRUNSWICK, 1999, 199 pages

Automatic detection of acoustic subword boundaries for single-digit recognition
 by Artimy, Maen Mohamed, MASc
 DALTECH-DALHOUSIE UNIVERSITY (CANADA), 1999, 94 pages

Design and implementation of a digital neural processor for detection applications
 by Balasubramanian, Balamurugan, MEng
 MEMORIAL UNIVERSITY OF NEWFOUNDLAND (CANADA), 1999, 138 pages

Tool cutting force modeling and wear estimation of micro-end-milling operations
 by Bao, Wei-Yu, PhD
 FLORIDA INTERNATIONAL UNIVERSITY, 1999, 199 pages

Hebbian learning in recurrent neural networks for natural language processing
 by Barilovits, Lottie Karlyn Ammons, PhD
 THE UNIVERSITY OF TENNESSEE, 1999, 185 pages

Motives and characteristics of gift-giving at the University of Nevada, Las Vegas
 by Belanger, Judy M., EdD
 UNIVERSITY OF NEVADA, LAS VEGAS, 1999, 172 pages

Knowledge-based magnetic resonance angiography
 by Bergman, Harris Lee, PhD
 GEORGIA INSTITUTE OF TECHNOLOGY, 1999, 186 pages

Frontal cortex mechanisms of visual selection
 by Bichot, Narcisse Pascal, PhD
 VANDERBILT UNIVERSITY, 1999, 373 pages

Adaptive modeling of legibility distance for symbolic warning signs
 by Bowen, Charles Kent, PhD
 TEXAS A&M UNIVERSITY, 1999, 160 pages

Artificially intelligent game client using neural networks
 by Brantley, Arrian Maximus, MEng
 UNIVERSITY OF LOUISVILLE, 1999, 71 pages

The hippocampus and parahippocampal cortices:  GABA(B) receptor-mediated modulation of principal cell excitability
 by Canning, Kevin James, PhD
 THE UNIVERSITY OF WESTERN ONTARIO (CANADA), 1999, 204 pages

A brain for language and the language of the brain
 by Cecchi, Guillermo Alberto, PhD
 THE ROCKEFELLER UNIVERSITY, 1999, 257 pages

Biomimetic robotics: Application of biological learning theories to mobile robot behaviors
 by Chang, Carolina, PhD
 BOSTON UNIVERSITY, 1999, 147 pages

Feature based reverse engineering employing automated multi-sensor scanning
 by Chan, Vincent Harry, PhD
 UNIVERSITY OF VICTORIA (CANADA), 1999, 148 pages

Seismic event picking for velocity estimation using neural networks
 by Cheng, Kuang-Zseng, PhD
 UNIVERSITY OF CALIFORNIA, DAVIS, 1999,  pages

Structure-function relationships in barley and malt starch: Influence on malting quality
 by Churchill, Karen Elizabeth, PhD
 UNIVERSITY OF MINNESOTA, 1999, 164 pages

Reducing samples and variables to train, test, and validate neural networks
 by Colmenares-Lacruz, Gerardo A., PhD
 UNIVERSITY OF SOUTH FLORIDA, 1999, 120 pages

Artificial neural network prediction of ground-level ozone concentration in Palm Beach County (Florida)
 by Crumiere, Mylene, MS
 FLORIDA ATLANTIC UNIVERSITY, 1999, 86 pages

Recognition of clutter in weather radars using polarization diversity information and artificial neural networks
 by Da Silveira, Reinaldo Bomfim, PhD
 UNIVERSITY OF ESSEX (UNITED KINGDOM), 1999,  pages

Image superresolution performance of multilayer feedforward neural networks
 by Davila, Carlos Antonio, PhD
 THE UNIVERSITY OF ARIZONA, 1999, 189 pages

Genetic optimization of neural network configurations for natural language learning
 by Davila, Jaime Jesus, PhD
 CITY UNIVERSITY OF NEW YORK, 1999, 95 pages

Computational studies of feeding behavior of Aplysia californica using a back-propagation model and a continuous time model with genetic algorithms
 by Deodhar, Dilip Nagesh, PhD
 COLUMBIA UNIVERSITY, 1999, 199 pages

Multistage fuzzy neural networks: Architectures, algorithms and analysis
 by Duan, Ji-cheng, PhD
 HONG KONG POLYTECHNIC UNIVERSITY (PEOPLE'S REPUBLIC OF CHINA), 1999, 160 pages

Neural network based smart antennas for cellular and mobile communications systems
 by El Zooghby, Ahmed Hassan, PhD
 UNIVERSITY OF CENTRAL FLORIDA, 1999, 137 pages

A simple, yet powerful neural equalizer
 by Enriquez, Leonel Ernesto, PhD
 FLORIDA INSTITUTE OF TECHNOLOGY, 1999, 301 pages

Control of vibration in switched reluctance motor drives
 by Fahimi, Babak, PhD
 TEXAS A&M UNIVERSITY, 1999, 100 pages

Neural network models of the brain mechanisms of bilateral coordination
 by Farrar, David Scott, PhD
 UNIVERSITY OF CALIFORNIA, SAN DIEGO, 1999, 90 pages

Neural network subpixel classification and estimation of multispectral images
 by Figueroa Quinones, Ricardo R., MS
 UNIVERSITY OF PUERTO RICO, MAYAGUEZ (PUERTO RICO), 1999, 115 pages

Novel aspects of neurotransmission in the developing neocortex
 by Flint, Alexander C., PhD
 COLUMBIA UNIVERSITY, 1999, 110 pages

Multidimensional resonance analysis of Lambda(+)/(c) going to pK(-)pi(+)
 by Fox, George Frederic, PhD
 UNIVERSITY OF SOUTH CAROLINA, 1999, 285 pages

Category induction and exception learning
 by Furl, Nicholas O., MS
 THE UNIVERSITY OF TEXAS AT ARLINGTON, 1999, 88 pages

An artificial neural network approach to the valuation of options and forecasting of volatility
 by Geigle, David S., DBA
 NOVA SOUTHEASTERN UNIVERSITY, 1999, 123 pages

Hydrolysis of butteroil by pregastric esterases immobilized in a hollow fiber reactor
 by Ghannouchi, Souheil, PhD
 THE UNIVERSITY OF WISCONSIN - MADISON, 1999, 592 pages

Analysis of a utility-interactive wind-photovoltaic hybrid system with battery storage using neural network
 by Giraud, Francois, DEng
 UNIVERSITY OF LOWELL, 1999, 143 pages

Real-time monitoring and adaptive control of CO(2) laser beam welding
 by Gu, Hongping, PhD
 UNIVERSITY OF WATERLOO (CANADA), 1999, 209 pages

Hybrid neural network first-principles approach to process modeling
 by Gupta, Sanjay, PhD
 UNIVERSITY OF FLORIDA, 1999, 113 pages

A theory of action potential generation in cortical neurons and its implication for neural activity
 by Gutkin, Boris Samuel, PhD
 UNIVERSITY OF PITTSBURGH, 1999, 194 pages

Examining the effect of communication on organizational learning using an artificial neural network model
 by Hamner, Marvine P., DSc
 WASHINGTON UNIVERSITY, 1999, 223 pages

Adaptive power system stabilizer based on recurrent neural network
 by He, Jian, PhD
 UNIVERSITY OF CALGARY (CANADA), 1999, 165 pages

Acoustic boundary control for quieter aircraft
 by Hirsch, Scott Michael, PhD
 UNIVERSITY OF DELAWARE, 1999, 154 pages

A framework for an automated neural network designer using evolutionary algorithms
 by Hlynka, Markian Denis, MSc
 THE UNIVERSITY OF MANITOBA (CANADA), 1999, 167 pages

Neural network based shaped neighborhoods: A design retrieval system
 by Holman, Frank Samuel, III, PhD
 UNIVERSITY OF WASHINGTON, 1999, 110 pages

Flight envelope limit detection and avoidance
 by Horn, Joseph Francis, PhD
 GEORGIA INSTITUTE OF TECHNOLOGY, 1999, 110 pages

Recursive learning for deformable object manipulation
 by Howard, Ayanna MacCalla, PhD
 UNIVERSITY OF SOUTHERN CALIFORNIA, 1999, 157 pages

Automatic updating of cartographic databases
 by Hsiao, Han-Wen, PhD
 UNIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN, 1999, 173 pages

Using an annealed neural network in organization personnel management
 by Huang, Kuo Kuang, EdD
 UNIVERSITY OF SOUTH DAKOTA, 1999, 118 pages

Prediction of mortality and in-hospital complications for acute myocardial infarction patients using artificial neural networks
 by Ismael, Mohammad Belall, PhD
 DUKE UNIVERSITY, 1999, 162 pages

Neural network model using a genetic algorithm to perform the functions of X-bar charts
 by Jackson, Neal Franklin, PhD
 THE UNIVERSITY OF MISSISSIPPI, 1999, 242 pages

Application of computational intelligence to power system security assessment
 by Jensen, Craig A., PhD
 UNIVERSITY OF WASHINGTON, 1999, 165 pages

Sliding-mode neural-network-inference fuzzy logic controller of nonlinear active suspension system
 by Joo, Dae Sung, DEng
 UNIVERSITY OF DETROIT MERCY, 1999, 194 pages

Detection of search and rescue targets in digitised multispectral imagery using artificial neural networks
 by Karim, Zulfiqar, MSc
 QUEEN'S UNIVERSITY AT KINGSTON (CANADA), 1999, 108 pages

Rapidly training device for fiber-optic neural network
 by Kashefi, Feraydun (Fred), PhD
 THE UNIVERSITY OF TEXAS AT DALLAS, 1999, 228 pages

Computer-aided diagnosis protocol for detection of pulmonary nodules in chest radiographs based on 'edge guided' wavelet snakes
 by Keserci, Muhammed Bilgin, PhD
 THE HERMAN M. FINCH U. OF HEALTH SCIENCES - THE CHICAGO MEDICAL SCH., 1999, 116 pages

Extensions of the generalized Hebbian algorithm
 by Kim, Inho, PhD
 FLORIDA INSTITUTE OF TECHNOLOGY, 1999, 147 pages

A partial correlation-based neural network learning paradigm
 by Kohen, Hamid S., PhD
 UNIVERSITY OF CALIFORNIA, LOS ANGELES, 1999, 90 pages

Image fusion using autoassociative-heteroassociative neural networks
 by Kropas-Hughes, Claudia V., PhD
 AIR FORCE INSTITUTE OF TECHNOLOGY, 1999, 132 pages

Design of artificial neural network for food safety and quality during thermal processing in a can
 by Kseibat, Dawod S., MSc
 UNIVERSITY OF GUELPH (CANADA), 1999, 116 pages

Development of animated finger movements via a neural network for tendon tension control
 by Kuchar, Olga Anna, PhD
 DALTECH-DALHOUSIE UNIVERSITY (CANADA), 1999, 108 pages

Optimal reliability centered vegetation maintenance scheduling in electric power distribution systems
 by Kuntz, Paul A., PhD
 UNIVERSITY OF WASHINGTON, 1999, 152 pages

Improved prediction and validation using resampled neural networks: Committee networks and hybrid validation
 by Lam, Sarah Shuk Yee, PhD
 UNIVERSITY OF PITTSBURGH, 1999, 321 pages

Policy subsystem portfolio management:  A neural network model of the Gulf of Mexico Program
 by Larkin, George Richard, PhD
 VIRGINIA POLYTECHNIC INSTITUTE AND STATE UNIVERSITY, 1999, 116 pages

An adaptive neural network controller for the articulated-body MMRC rover
 by Lee, Songjae, PhD
 NORTH CAROLINA STATE UNIVERSITY, 1999, 143 pages

The integration and segmentation of visual motion signals: Experiments and a computational model of cortical mechanisms
 by Liden, Lars H., PhD
 BOSTON UNIVERSITY, 1999, 169 pages

Artificial neural networks applied for wind power estimation and forecast
 by Li, Shuhui , PhD
 TEXAS TECH UNIVERSITY, 1999, 128 pages

Fully parallel learning neural network chip for real-time control
 by Liu, Jin, PhD
 GEORGIA INSTITUTE OF TECHNOLOGY, 1999, 316 pages

Bayesian classification using noninformative Dirichlet priors
 by Lynch, Robert Stephen, Jr., PhD
 THE UNIVERSITY OF CONNECTICUT, 1999, 114 pages

Stable neural network control of structurally flexible space manipulators:  A novel approach featuring fast training and efficient memory
 by Macnab, Chris John Brent, PhD
 UNIVERSITY OF TORONTO (CANADA), 1999, 137 pages

Comparative analysis of neural networks and traditional actuarial methods for estimating casualty insurance reserve liability
 by Magee, David Douglas, PhD
 THE UNIVERSITY OF TEXAS AT AUSTIN, 1999, 123 pages

Neural networks for satellite remote sensing and robotic sensor interpretation
 by Martens, Siegfried, PhD
 BOSTON UNIVERSITY, 1999, 143 pages

Neural network-based multimode fiber optic image transmission
 by Marusarz, Ronald Karl, PhD
 SOUTHERN ILLINOIS UNIVERSITY AT CARBONDALE, 1999, 101 pages

Adaptive visual representations for autonomous mobile robots using competitive learning algorithms
 by McNeill, Dean Kevin, PhD
 THE UNIVERSITY OF MANITOBA (CANADA), 1999, 122 pages

Learning helicopter control through 'teaching by showing
 by Montgomery, James Flavil, PhD
 UNIVERSITY OF SOUTHERN CALIFORNIA, 1999, 221 pages

Visualizing speech with a recurrent neural network trained on human acoustic-articulatory data
 by Moody, Jay Tucker, PhD
 UNIVERSITY OF CALIFORNIA, SAN DIEGO, 1999, 122 pages

Feedforward, feedback neural networks with context-driven segmentation and recognition
 by Neskovic, Predrag, PhD
 BROWN UNIVERSITY, 1999, 156 pages

Field testing and monitoring of full-scale drilled shafts subjected to lateral loads
 by Nusairat, Jamal Hassan, PhD
 THE UNIVERSITY OF AKRON, 1999, 389 pages

Nonlinear modeling and analysis of highly varying loads
 by O'Neill Carrillo, Efrain, PhD
 ARIZONA STATE UNIVERSITY, 1999, 143 pages

The development of an exposure measurement system for assessing risk of work-related musculoskeletal disorders (WMSDs)
 by Park, Seikwon, PhD
 THE PENNSYLVANIA STATE UNIVERSITY, 1999, 267 pages

Adaptive exploration in reinforcement learning
 by Patrascu, Relu-Eugen, MSc
 UNIVERSITY OF GUELPH (CANADA), 1999, 78 pages

Neural network-based modeling of synchronous machines from on-line operating data
 by Pillutla, Srinivas, PhD
 THE OHIO STATE UNIVERSITY, 1999, 133 pages

Neural networks in the analysis of water-soluble sulfonylurea herbicides using an LC/MS
 by Pompano, Joseph Michael, PhD
 VIRGINIA COMMONWEALTH UNIVERSITY, 1999, 178 pages

Log-adaptive filters: Stochastic analysis and design
 by Rakijas, Michael, PhD
 UNIVERSITY OF CALIFORNIA, IRVINE, 1999, 227 pages

Improving generalization of constructive neural networks using ensembles
 by Renner, Renee Stoneking, PhD
 THE FLORIDA STATE UNIVERSITY, 1999, 248 pages

Mathematical foundations of simple recurrent networks in language processing
 by Rodriguez, Paul Fabian, PhD
 UNIVERSITY OF CALIFORNIA, SAN DIEGO, 1999, 179 pages

Prediction of dynamic bending stresses of ships at sea
 by Rogers, Frederick Phillip, MEng
 MEMORIAL UNIVERSITY OF NEWFOUNDLAND (CANADA), 1999, 116 pages

Target recognition using neural networks for wind tunnel model deformation measurements
 by Ross, Richard William, MS
 CHRISTOPHER NEWPORT UNIVERSITY, 1999, 145 pages

Inversion for explanation capability of neural networks and query-based learning
 by Saad, Emad William, PhD
 TEXAS TECH UNIVERSITY, 1999, 94 pages

Modeling water distribution pipe failures using artificial neural networks
 by Sacluti, Fernando Revilla, MSc
 UNIVERSITY OF ALBERTA (CANADA), 1999, 148 pages

Spiking neurons and the temporal aspect of neural networks
 by Sala, Dorel Mario, PhD
 THE UNIVERSITY OF TOLEDO, 1999, 86 pages

Recognizing moving objects: A neural model of temporal binding in human vision
 by Schmitt, Charles Patrick, PhD
 THE UNIVERSITY OF NORTH CAROLINA AT CHAPEL HILL, 1999, 247 pages

Predicting enzyme function from sequence
 by Shah, Imran, PhD
 GEORGE MASON UNIVERSITY, 1999, 280 pages

An intelligent neural network forecaster to predict the Standard & Poor 500's index
 by Shah, Sulay Bipin, MS
 FLORIDA ATLANTIC UNIVERSITY, 1999, 144 pages

A new methodology to predict certain characteristics of stock market using time-series phenomena
 by Shah, Trupti U., MS
 FLORIDA ATLANTIC UNIVERSITY, 1999, 126 pages

Multiresolution content-based image retrieval and clustering in large visual databases
 by Sheikholeslami, Gholamhosein, PhD
 STATE UNIVERSITY OF NEW YORK AT BUFFALO, 1999, 241 pages

Optimal control of nonlinear systems with neural networks
 by Shen, Raymond Tei-Luen, PhD
 STANFORD UNIVERSITY, 1999, 96 pages

Spatial decision support system for integrated river basin flood control
 by Shim, Kyn-Cheoul, PhD
 COLORADO STATE UNIVERSITY, 1999, 245 pages

Cognitive and physiological aspects of attention to personally relevant negative information in depression
 by Siegle, Greg Jeremy, PhD
 UNIVERSITY OF CALIFORNIA, SAN DIEGO, 1999, 203 pages

Neural network analysis of long-range precipitation forecasts
 by Silverman, David I., PhD
 UNIVERSITY OF CALIFORNIA, LOS ANGELES, 1999, 99 pages

Modeling for control of a water treatment plant using neural network approach
 by Singhvi, Sanjay Sajjansingh, PhD
 THE UNIVERSITY OF IOWA, 1999, 250 pages

Application of the Hopfield neural network in routing for computer networks
 by Smeda, Adel Abdullah, MASc
 DALTECH-DALHOUSIE UNIVERSITY (CANADA), 1999, 77 pages

Neural network solutions to the ocean optics inverse problem
 by Smith, Walter Frazier, Jr., PhD
 THE UNIVERSITY OF SOUTHERN MISSISSIPPI, 1999, 111 pages

Modeling, evaluation, and transfer of human control strategy
 by Song, Jingyan, PhD
 CHINESE UNIVERSITY OF HONG KONG (PEOPLE'S REPUBLIC OF CHINA), 1999, 118 pages

A probabilistic neural network computer vision system for corn kernel damage evaluation
 by Steenhoek, Loren W., PhD
 IOWA STATE UNIVERSITY, 1999, 66 pages

A ground-based real-time remote sensing system for diagnosing nitrogen status in cotton plants
 by Sui, Ruixiu, PhD
 THE UNIVERSITY OF TENNESSEE, 1999, 123 pages

Maximum entropy-based optimization of artificial neural networks: An application to ATM telecommunication parameter predictions
 by Sundaram, Karthik, MS
 FLORIDA ATLANTIC UNIVERSITY, 1999, 145 pages

Frequency-diverse ultrasonic target detection using Bayes, fuzzy discriminant, and neural network classifiers
 by Sun, Han Chieh, PhD
 ILLINOIS INSTITUTE OF TECHNOLOGY, 1999, 121 pages

A fast radio transmitter identification system
 by Sun, Luotao, MSc
 THE UNIVERSITY OF MANITOBA (CANADA), 1999, 302 pages

Integrating modelling techniques for financial time series
 by Tan, Victor Khoon Lee, PhD
 UNIVERSITY OF GUELPH (CANADA), 1999, 82 pages

Neural networks for speech recognition of a phonetic language
 by Teshome, Dagnachew, MS
 CALIFORNIA STATE UNIVERSITY, LONG BEACH, 1999, 55 pages

A parallel observer system for multirate state estimation and aliased output measurements
 by Thein, May-Win Lwin, PhD
 OKLAHOMA STATE UNIVERSITY, 1999, 193 pages

Multi-objective fuzzy regression and its application to erosion prediction
 by Tran, Liem Thanh, PhD
 UNIVERSITY OF HAWAII, 1999, 196 pages

Event shape variables and neural network identification of event types in electron-positron collisions near 10 GeV
 by Trunov, Artem G., MS
 UNIVERSITY OF LOUISVILLE, 1999, 69 pages

A flexible feature-based design retrieval system
 by Tsai, Chieh-Yuan, PhD
 UNIVERSITY OF MISSOURI - COLUMBIA, 1999, 152 pages

Adaptive combination of evidence for information retrieval
 by Vogt, Christopher Charles, PhD
 UNIVERSITY OF CALIFORNIA, SAN DIEGO, 1999, 169 pages

A speaker recognition method based on RBF neural networks and perceptual processing
 by Walkowiak, Tomasz, DrInz
 POLITECHNIKA WROCLAWSKA (POLAND), 1999, 80 pages

Knowledge-based neural networks for microwave modeling and design
 by Wang, Fang , PhD
 CARLETON UNIVERSITY (CANADA), 1999, 176 pages

Neural network-based control strategies for a two-CSTR-in-series system
 by Wang, Wentao, MS
 UNIVERSITY OF LOWELL, 1999, 182 pages

Fuzzy neural network for edge detection and Hopfield network for edge enhancement
 by Wang, Ziqing, MSc
 MEMORIAL UNIVERSITY OF NEWFOUNDLAND (CANADA), 1999, 143 pages

Motion control in an open architecture environment
 by Weller, Edward A., PhD
 UNIVERSITY OF VIRGINIA, 1999, 153 pages

Autonomous real-time detection of silent ischemia
 by Wheelock, Bryan Martin, MSE
 UNIVERSITY OF ALABAMA IN HUNTSVILLE, 1999, 76 pages

Dynamic filtering of recognition memory codes in the hippocampus: Evidence from unit recording and neural network modeling
 by Wiebe, Sherman Perry, PhD
 NEW YORK UNIVERSITY, 1999, 146 pages

Choice of techniques in data mining: Three experiments in applications
 by Wu, Hong, MS
 THE AMERICAN UNIVERSITY, 1999, 50 pages

Encoding of sound-source elevation by the spike patterns of cortical neurons
 by Xu, Li, PhD
 UNIVERSITY OF FLORIDA, 1999, 134 pages

Surface EMG decomposition based on artificial neural network
 by Xu, Zheng-quan, PhD
 HONG KONG POLYTECHNIC UNIVERSITY (PEOPLE'S REPUBLIC OF CHINA), 1999, 134 pages

Pattern recognition and classification of vibrational spectra by artificial neural networks
 by Yang, Husheng, PhD
 UNIVERSITY OF IDAHO, 1999, 161 pages

Adaptive agents for information retrieval and data-driven knowledge discovery
 by Yang, Jihoon, PhD
 IOWA STATE UNIVERSITY, 1999, 161 pages

Bandwidth allocation in ATM networks using neural networks
 by Youssef, Sameh Ahmed, PhD
 CITY UNIVERSITY OF NEW YORK, 1999, 82 pages

Robust speech recognition using neural networks and hidden Markov models: Adaptations using nonlinear transformations
 by Yuk, Dongsuk, PhD
 RUTGERS THE STATE UNIVERSITY OF NEW JERSEY - NEW BRUNSWICK, 1999, 106 pages

Development of a methodology to evaluate reservoir quality from well logs in lithologically highly complex formation: Evaluation of reservoir quality in
 the Mardie Greensand, Carnarvon Basin, Western Australia
 by Zhang, Yujin, PhD
 UNIVERSITY OF NEW SOUTH WALES (AUSTRALIA), 1999,  pages