488 Matching Results

Search Results

Advanced search parameters have been applied.

Computational Complexity of Hopfield Networks

Description: There are three main results in this dissertation. They are PLS-completeness of discrete Hopfield network convergence with eight different restrictions, (degree 3, bipartite and degree 3, 8-neighbor mesh, dual of the knight's graph, hypercube, butterfly, cube-connected cycles and shuffle-exchange), exponential convergence behavior of discrete Hopfield network, and simulation of Turing machines by discrete Hopfield Network.
Date: August 1998
Creator: Tseng, Hung-Li
Partner: UNT Libraries

Neural Networks for Analysis of Top Quark Production

Description: Neural networks (NNs) provide a powerful and flexible tool for selecting a signal from a larger background. The D0 collaboration has used them extensively in studying t{anti t} decays. NNs were essential to the measurement of the t{anti t} production cross section in the all-jets channel (t{anti t} {yields} b {anti b}qqqq), and were also used in the measurement of the mass of the top quark in the lepton+jets channel (t{anti t} {yields} b{anti b}l{nu}q{anti q}). This paper will describe two new applications of neural networks to top quark analysis: the search for single top quark production, and an effort to increase the sensitivity in the dilepton channel t{anti t} {yields} b{anti b}e{anti {mu}}{nu}{anti {nu}} beyond that achieved in the published analysis.
Date: August 4, 1999
Creator: al., B. Abbott et
Partner: UNT Libraries Government Documents Department

Exploration of hierarchical leadership and connectivity in neural networks in vitro.

Description: Living neural networks are capable of processing information much faster than a modern computer, despite running at significantly lower clock speeds. Therefore, understanding the mechanisms neural networks utilize is an issue of substantial importance. Neuronal interaction dynamics were studied using histiotypic networks growing on microelectrode arrays in vitro. Hierarchical relationships were explored using bursting (when many neurons fire in a short time frame) dynamics, pairwise neuronal activation, and information theoretic measures. Together, these methods reveal that global network activity results from ignition by a small group of burst leader neurons, which form a primary circuit that is responsible for initiating most network-wide burst events. Phase delays between leaders and followers reveal information about the nature of the connection between the two. Physical distance from a burst leader appears to be an important factor in follower response dynamics. Information theory reveals that mutual information between neuronal pairs is also a function of physical distance. Activation relationships in developing networks were studied and plating density was found to play an important role in network connectivity development. These measures provide unique views of network connectivity and hierarchical relationship in vitro which should be included in biologically meaningful models of neural networks.
Date: December 2008
Creator: Ham, Michael I.
Partner: UNT Libraries

Reservoir Characterization of Upper Devonian Gordon Sandstone, Jacksonburg, Stringtown Oil Field, Northwestern West Virginia

Description: This report gives results on use of a minipermeameter on cores to study very finescale trends in permeability, and use of neural networks to predict permeability in logged, uncored wells.
Date: May 21, 2002
Creator: Ameri, S.; Aminian, K.; Avary, K.L.; Bilgesu, H.I.; Hohn, M.E.; McDowell, R.R. et al.
Partner: UNT Libraries Government Documents Department

Neural Network method for Inverse Modeling of Material Deformation

Description: A method is described for inverse modeling of material deformation in applications of importance to the sheet metal forming industry. The method was developed in order to assess the feasibility of utilizing empirical data in the early stages of the design process as an alternative to conventional prototyping methods. Because properly prepared and employed artificial neural networks (ANN) were known to be capable of codifying and generalizing large bodies of empirical data, they were the natural choice for the application. The product of the work described here is a desktop ANN system that can produce in one pass an accurate die design for a user-specified part shape.
Date: July 10, 1999
Creator: Allen, J.D., Jr.; Ivezic, N.D. & Zacharia, T.
Partner: UNT Libraries Government Documents Department

Neural Network Modeling of Weld Pool Shape in Pulsed-Laser Aluminum Welds

Description: A neural network model was developed to predict the weld pool shape for pulsed-laser aluminum welds. Several different network architectures were examined and the optimum architecture was identified. The neural network was then trained and, in spite of the small size of the training data set, the network accurately predicted the weld pool shape profiles. The neural network output was in the form of four weld pool shape parameters (depth, width, half-width, and area) and these were converted into predicted weld pool profiles with the use of the actual experimental poo1 profiles as templates. It was also shown that the neural network model could reliably predict the change from conduction-mode type shapes to keyhole-mode shapes.
Date: November 16, 1998
Creator: Iskander, Y.S.; Oblow, E.M. & Vitek, J.M.
Partner: UNT Libraries Government Documents Department

Event identification from seismic/magnetic feature vectors: a comparative study

Description: The event identification problem plays a large role in the application of unattended ground sensors to the monitoring of borders and checkpoints. The choice of features and methods for classifying features affects how accurately these classifications are made. Finding features which reliably distinguish events of interest may require measurements based on separate physical phenomena. Classification methods include neural net versus fuzzy logic approaches, and within the neural category, different architectures and transfer functions for reaching decisions. This study examines ways of optimizing feature sets and surveys common techniques for classifying feature vectors corresponding to physical events. We apply each technique to samples of existing data, and compare discrimination attributes. Specifically, we calculate the confusion matrices for each technique applied to each sample dataset, and reduce them statistically to scalar scores. In addition, we gauge how the accuracy of each method is degraded by reducing the feature vector length by one element. Finally, we gather rough estimates of the relative cpu performance of the forward prediction algorithms.
Date: April 1, 1997
Creator: Wolford, J. K.
Partner: UNT Libraries Government Documents Department

Concentration-dependent Effects of D-Methylphenidate on Frontal Cortex and Spinal Cord Networks in vitro

Description: Spontaneously active frontal cortex and spinal cord networks grown on microelectrode arrays were used to study effects of D-methylphenidate. These central nervous system tissues have relatively low concentrations of dopaminergic and noradrenergic neurons compared to the richly populated loci, yet exhibit similar neurophysiological responses to methylphenidate. The spontaneous spike activity of both tissues was inhibited in a concentration-dependent manner by serial additions of 1-500 µM methylphenidate. Methylphenidate is non-toxic as spike inhibition was recovered following washes. The average concentrations for 50% spike rate inhibition (IC50 ± SD) were 118 ± 52 (n= 6) and 57 ± 43 (n = 11) for frontal cortex and spinal cord networks, respectively. A 3 hour exposure of a network to 1 mM methylphenidate was nontoxic. The effective concentrations described in this study are within the therapeutic dosage range. Therefore, the platform may be used for further investigations of drug mechanisms.
Date: December 2004
Creator: Miller, Benjamin R.
Partner: UNT Libraries

Distinguishing Sedimentary Depositional Environments on Mars Using In-Situ Luminescence Measurements and Neural Network Analysis.

Description: Although not recognized as a true geologic period on Mars, the term 'Martian Quaternary' emerged at the 2001 LPSC. The phrase helps focus attention on the fact that Mars does indeed exhibit dynamic surface processes andd geomorphic features active on time scales less than 10{sup 6} years. As on earth evolving landscapes can serve as important storehouses for paltoclimatic and paIeoenvironmental records. However, deciphering the 'Quaternary' history of Mars will require the development of 4 new set of tools that are uniquely suited to examining youthful sediments and geomorphic features.
Date: January 1, 2001
Creator: Lepper, K. E. (Kenneth E.) & Whitley, V. H. (Von H.)
Partner: UNT Libraries Government Documents Department

Temporal Connectionist Expert Systems Using a Temporal Backpropagation Algorithm

Description: Representing time has been considered a general problem for artificial intelligence research for many years. More recently, the question of representing time has become increasingly important in representing human decision making process through connectionist expert systems. Because most human behaviors unfold over time, any attempt to represent expert performance, without considering its temporal nature, can often lead to incorrect results. A temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems, has been introduced. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications. A temporal backpropagation algorithm which supports the model has been developed. The model along with the temporal backpropagation algorithm makes it extremely practical to define any artificial neural network application. Also, an approach that can be followed to decrease the memory space used by weight matrix has been introduced. The algorithm was tested using a medical connectionist expert system to show how best we describe not only the disease but also the entire course of the disease. The system, first, was trained using a pattern that was encoded from the expert system knowledge base rules. Following then, series of experiments were carried out using the temporal model and the temporal backpropagation algorithm. The first series of experiments was done to determine if the training process worked as predicted. In the second series of experiments, the weight matrix in the trained system was defined as a function of time intervals before presenting the system with the learned patterns. The result of the two experiments indicate that both approaches produce correct results. The only difference between the two results ...
Date: December 1993
Creator: Civelek, Ferda N. (Ferda Nur)
Partner: UNT Libraries

Advanced Signal Analysis for Forensic Applications of Ground Penetrating Radar

Description: Ground penetrating radar (GPR) systems have traditionally been used to image subsurface objects. The main focus of this paper is to evaluate an advanced signal analysis technique. Instead of compiling spatial data for the analysis, this technique conducts object recognition procedures based on spectral statistics. The identification feature of an object type is formed from the training vectors by a singular-value decomposition procedure. To illustrate its capability, this procedure is applied to experimental data and compared to the performance of the neural-network approach.
Date: June 2004
Creator: Koppenjan, Steven; Streeton, Matthew; Lee, Hua; Lee, Michael & Ono, Sashi
Partner: UNT Libraries Government Documents Department

Identifying generalities in data sets using periodic Hopfield networks : initial status report.

Description: We present a novel class of dynamic neural networks that is capable of learning, in an unsupervised manner, attractors that correspond to generalities in a data set. Upon presentation of a test stimulus, the networks follow a sequence of attractors that correspond to subsets of increasing size or generality in the original data set. The networks, inspired by those of the insect antennal lobe, build upon a modified Hopfield network in which nodes are periodically suppressed, global inhibition is gradually strengthened, and the weight of input neurons is gradually decreased relative to recurrent connections. This allows the networks to converge on a Hopfield network's equilibrium within each suppression cycle, and to switch between attractors in between cycles. The fast mutually reinforcing excitatory connections that dominate dynamics within cycles ensures the robust error-tolerant behavior that characterizes Hopfield networks. The cyclic inhibition releases the network from what would otherwise be stable equilibriums or attractors. Increasing global inhibition and decreasing dependence on the input leads successive attractors to differ, and to display increasing generality. As the network is faced with stronger inhibition, only neurons connected with stronger mutually excitatory connections will remain on; successive attractors will consist of sets of neurons that are more strongly correlated, and will tend to select increasingly generic characteristics of the data. Using artificial data, we were able to identify configurations of the network that appeared to produce a sequence of increasingly general results. The next logical steps are to apply these networks to suitable real-world data that can be characterized by a hierarchy of increasing generality and observe the network's performance. This report describes the work, data, and results, the current understanding of the results, and how the work could be continued. The code, data, and preliminary results are included and are available as an archive.
Date: December 1, 2004
Creator: Link, Hamilton E. & Backer, Alejandro
Partner: UNT Libraries Government Documents Department

A Multi-Time Scale Learning Mechanism for Neuromimic Processing

Description: Learning and representing and reasoning about temporal relations, particularly causal relations, is a deep problem in artificial intelligence (AI). Learning such representations in the real world is complicated by the fact that phenomena are subject to multiple time scale influences and may operate with a strange attractor dynamic. This dissertation proposes a new computational learning mechanism, the adaptrode, which, used in a neuromimic processing architecture may help to solve some of these problems. The adaptrode is shown to emulate the dynamics of real biological synapses and represents a significant departure from the classical weighted input scheme of conventional artificial neural networks. Indeed the adaptrode is shown, by analysis of the deep structure of real synapses, to have a strong structural correspondence with the latter in terms of multi-time scale biophysical processes. Simulations of an adaptrode-based neuron and a small network of neurons are shown to have the same learning capabilities as invertebrate animals in classical conditioning. Classical conditioning is considered a fundamental learning task in animals. Furthermore, it is subject to temporal ordering constraints that fulfill the criteria of causal relations in natural systems. It may offer clues to the learning of causal relations and mechanisms for causal reasoning. The adaptrode is shown to solve an advanced problem in classical conditioning that addresses the problem of real world dynamics. A network is able to learn multiple, contrary associations that separate in time domains, that is a long-term memory can co-exist with a short-term contrary memory without destroying the former. This solves the problem of how to deal with meaningful transients while maintaining long-term memories. Possible applications of adaptrode-based neural networks are explored and suggestions for future research are made.
Date: August 1994
Creator: Mobus, George E. (George Edward)
Partner: UNT Libraries

Medial Medulla Networks in Culture: a Multichannel Electrophysiologic and Pharmacological Study

Description: Spontaneously active primary cultures obtained from dissociated embryonic medial medulla tissue were grown on microelectrode arrays for investigating burst patterns and pharmacological responses of respiratory-related neurons. Multichannel burst rates and spike production were used as primary variables for analysis. Pacemaker-like neurons were identified by continued spiking under low Ca++/high Mg++conditions. The number of pacemakers increased with time under synaptic blocking medium. Sensitivity to CO2 levels was found in some neurons. Acetylcholine changed activity in a complex fashion. Curare, atropine and gallamine modified ACh effects. Eserine alone was ineffective, but potentiated ACh-induced responses. Norepinephrine caused channel-specific increases or decreases, whereas dopamine and serotonin had little effect at 30 μM. GABA and glycine stopped most spiking at 70 μM. Developmental changes in glycine sensitivity (increasing with age) were also observed. It is concluded that pacemaker and chemosensitive neurons develop in medial medulla cultures, and that these cultures are pharmacologically histiotypic.
Date: August 1998
Creator: Keefer, Edward W. (Edward Wesley)
Partner: UNT Libraries

A neural computation approach to the set covering problem

Description: This paper presents a neural network algorithm which is capable of finding approximate solutions for unicost set covering problems. The network has two types of units (neurons), with different dynamics and activation functions. One type represents the objects to be covered (the rows in the matrix representation of the problem) and another represents the ``covering`` sets (the 0,1 variables). They are connected as a bipartite graph which represents the incidence relations between objects and sets (i.e the 0,1 adjacency matrix). When the parameters of the units are correctly tuned, the stable states of the system correspond to the minimal covers. I show that in its basic mode of operation, descent dynamics, when the network is set in an arbitrary initial state it converges in less than 2n steps (where n is the number of variables), to a stable state which represents a valid solution. In this mode, the network implements a greedy heuristic in which the choice function is based on the unit inputs (which are determined by the activation functions and the network state). On top of the basic network dynamics, the algorithm applies an adaptive restart procedure which helps to search more effectively for ``good`` initial states and results in better performance.
Date: July 1, 1995
Creator: Grossman, T.
Partner: UNT Libraries Government Documents Department

Image and video compression/decompression based on human visual perception system and transform coding

Description: The quantity of information has been growing exponentially, and the form and mix of information have been shifting into the image and video areas. However, neither the storage media nor the available bandwidth can accommodated the vastly expanding requirements for image information. A vital, enabling technology here is compression/decompression. Our compression work is based on a combination of feature-based algorithms inspired by the human visual- perception system (HVS), and some transform-based algorithms (such as our enhanced discrete cosine transform, wavelet transforms), vector quantization and neural networks. All our work was done on desktop workstations using the C++ programming language and commercially available software. During FY 1996, we explored and implemented an enhanced feature-based algorithms, vector quantization, and neural- network-based compression technologies. For example, we improved the feature compression for our feature-based algorithms by a factor of two to ten, a substantial improvement. We also found some promising results when using neural networks and applying them to some video sequences. In addition, we also investigated objective measures to characterize compression results, because traditional means such as the peak signal- to-noise ratio (PSNR) are not adequate to fully characterize the results, since such measures do not take into account the details of human visual perception. We have successfully used our one- year LDRD funding as seed money to explore new research ideas and concepts, the results of this work have led us to obtain external funding from the dud. At this point, we are seeking matching funds from DOE to match the dud funding so that we can bring such technologies into fruition. 9 figs., 2 tabs.
Date: February 1, 1997
Creator: Fu, Chi Yung., Petrich, L.I., Lee, M.
Partner: UNT Libraries Government Documents Department

Detection and Location of Structural Degradation in Mechanical Systems

Description: The investigation of a diagnostic method for detecting and locating the source of structural degradation in a mechanical system is described in this paper. The diagnostic method uses a mathematical model of the mechanical system to determine relationships between system parameters and measurable spectral features. These relationships are incorporated into a neural network, which associates measured spectral features with system parameters. Condition diagnosis is performed by presenting the neural network with measured spectral features and comparing the system parameters estimated by the neural network to previously estimated values. Changes in the estimated system parameters indicate the location and severity of degradation in the mechanical system.
Date: August 30, 1999
Creator: Blakeman, E.D.; Damiano, B. & Phillips, L.D.
Partner: UNT Libraries Government Documents Department

Word prediction

Description: In this project we have developed a language model based on Artificial Neural Networks (ANNs) for use in conjunction with automatic textual search or speech recognition systems. The model can be trained on large corpora of text to produce probability estimates that would improve the ability of systems to identify words in a sentence given partial contextual information. The model uses a gradient-descent learning procedure to develop a metric of similarity among terms in a corpus, based on context. Using lexical categories based on this metric, a network can then be trained to do serial word probability estimation. Such a metric can also be used to improve the performance of topic-based search by allowing retrieval of information that is related to desired topics even if no obvious set of key words unites all the retrieved items.
Date: May 1, 1995
Creator: Rumelhart, D.E.; Skokowski, P.G. & Martin, B.O.
Partner: UNT Libraries Government Documents Department

Analysis of insider threats against computerized nuclear materials accountability applications

Description: DOE Order 5633.3B requires that nuclear material accountability (MA) systems provide for (1) tracking material inventories, (2) documenting material transactions, (3) issuing periodic reports, and (4) assisting in the detection of- unauthorized system access, data falsification, and material gains or losses. Insider threats against the MA system represent the potential to degrade the integrity with which these requirements are addressed (e.g., altering data to misrepresent the quantity or location of nuclear material). In this paper, we describe a methodology for evaluating potential insider threats against both current and future (e.g., client-server network) MA software applications. The methodology comprises a detail yet practical taxonomy for characterizing various types of MA system/software applications and their implementation options. This taxonomy facilitates the systematic collection and organization of key information that helps spotlight such things as stag of information flow, transaction procedures, or auditing procedures potentially susceptible to inside falsification. Methodology benefits include helping MA managers and policy makers: (1) examine proposed software designs or modifications with respect to how they might reduce or increase exposure to insider threats; and (2) better understand safeguards cost (e.g., operational hindrances) and benefit (resistance to falsification) tradeoffs of different system/software alternatives.
Date: July 1, 1995
Creator: Jones, E. & Sicherman, A.
Partner: UNT Libraries Government Documents Department

A novel microsatellite control system

Description: The authors are researching extremely simple yet quite capable analog pulse-coded neural networks for ``smaller-faster-cheaper`` spacecraft attitude and control systems. The will demonstrate a prototype microsatellite that uses their novel control method to autonomously stabilize itself in the ambient magnetic field and point itself at the brightest available light source. Though still in design infancy, the ``Nervous Net`` controllers described could allow for space missions not currently possible given conventional satellite hardware. Result, prospects and details are presented.
Date: February 1, 1998
Creator: Moore, K.R.; Frigo, J.R. & Tilden, M.W.
Partner: UNT Libraries Government Documents Department

Super synchronization for fused video and time-series neural network training

Description: A key element in establishing neural networks for traffic monitoring is the ground truth data set that verifies the sensor data. The sensors we use have time series data gathered from loop and piezo sensors embedded in the highway. These signals are analyzed and parsed into vehicle events. Features are extracted from these sensors and combine to form the vehicle vectors. The vehicle vectors are combined together with the video data in a data fusion process thereby providing the neural network with its training set. We examine two studies, one by Georgia Tech Research Institute (GTRI) and another by Los Alamos National Laboratory (LANL) that use video information and have had difficulties in establishing the fusion process. That is to say, the correspondence between the video events recorded as the ground truth data and the sensor events has been uncertain. We show that these uncertainties can be removed by establishing a more precise and accurate time measurement for the video events. The principal that the video time information is inherently precise to better than a frame (1/30 s) and that by tracing the factors causing imprecision in the timing of events, we can achieve precisions required for unique vehicle identification we call super synchronization. In the Georgia data study there was an imprecision on the order of 3 seconds and in the LANL study an imprecision of early a second. In both cases, the imprecision had led to lack of proper identification of sensor events. In the case of the Georgia 120 study sensors were placed at various distances downstream, up to 250 meters, from the ground truth camera. The original analysis assumed that there was a fixed time offset corresponding to the downstream location. For this case we show that when we restrict the analysis to passenger cars and ...
Date: June 1, 1996
Creator: Elliott, C.J.; Pepin, J. & Gillmann, R.
Partner: UNT Libraries Government Documents Department