SEARCH · PubMed Health

Results for “Neural Networks, Computer”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 559 records · Page 31Linked to original sources

PubMed2003

SC-CNNs for chaotic signal applications in secure communication systems.

In this paper a CNNs based circuit for the generation of hyperchaotic signals is proposed. The circuit has been developed for applications in secure communication systems. An Saito oscillator has been designed by using a suitable configuration of a four-cells State-Controlled CNNs. A cryptography system based on the Saito oscillator has been implemented by using inverse system synchronization. The proposed circuit implementation and experimental results are given.

Computer Communication Networks↗

PubMed1993

A gradient system solution to Potts mean field equations and its electronic implementation.

A gradient system solution method is presented for solving Potts mean field equations for combinatorial optimization problems subject to winner-take-all constraints. In the proposed solution method the optimum solution is searched by using gradient descent differential equations whose trajectory is confined within the feasible solution space of optimization problems. This gradient system is proven theoretically to always produce a legal local optimum solution of combinatorial optimization problems. An elementary analog electronic circuit implementing the presented method is designed on the basis of current-mode subthreshold MOS technologies. The core constituent of the circuit is the winner-take-all circuit developed by Lazzaro et al. Correct functioning of the presented circuit is exemplified with simulations of the circuits implementing the scheme for solving the shortest path problems.

Algorithms↗

PubMed1993

A rule-based neural controller for inverted pendulum system.

This paper tries to demonstrate how a heuristic neural control approach can be used to solve a complex nonlinear control problem. The control task is to swing up a pendulum mounted on a cart from its stable position (vertically down) to the zero state (up right) and keep it there by applying a sequence of two opposing constant forces of equal magnitude to the mass center of the cart. In addition, the displacement of the cart itself is confined to within a preset limit during the swinging up action and it will eventually be brought to the origin of the track. This is truly a nontrivial nonlinear regulation problem and is considerably difficult compared to the pendulum balancing problem (and its variations) widely adopted as a benchmarking test system for neural controllers. Through the solution of this specific control problem, we try to illustrate a heuristic neural control approach with task decomposition, control rule extraction and neural net rule implementation as its basic elements. Specializing to the pendulum problem, the global control task is decomposed into subtasks namely pendulum positioning and cart positioning. Accordingly, three separate neural subcontrollers are designed to cater to the subtasks and their coordination, i.e., pendulum subcontroller (PSC), cart subcontroller (CSC) and the switching subcontroller (SSC). Each of the subcontrollers is designed based on the rules and guidelines obtained from the experiences of a human operator. The simulation result is included to show the actual performance of the controller.

Algorithms↗

PubMed1993

Multiprocessor and memory architecture of the neurocomputer SYNAPSE-1.

A general purpose neurocomputer, SYNAPSE-1, which exhibits a multiprocessor and memory architecture is presented. It offers wide flexibility with respect to neural algorithms and a speed-up factor of several orders of magnitude--including learning. The computational power is provided by a 2-dimensional systolic array of neural signal processors. Since the weights are stored outside these NSPs, memory size and processing power can be adapted individually to the application needs. A neural algorithms programming language, embedded in C(+2) has been defined for the user to cope with the neurocomputer. In a benchmark test, the prototype of SYNAPSE-1 was 8000 times as fast as a standard workstation.

Algorithms↗

PubMed1993

Using coherent pulse width and edge modulations in artificial neural systems.

This paper describes an existing silicon implementation of an artificial neural system based on coherent pulse width and edge modulation techniques. A chip set with different neural functions has been conceived, manufactured and tested. Neural circuits have been optimized for lowest computation energy and highest reconfigurability. The main device is a 32 x 32 synaptic array consuming 10 mW of power at 140 MCPS. Synapsis size is about 7.200 microns 2 using a standard 1.5 microns CMOS technology. The problem of interfacing robotic sensors and actuators is addressed: voltage, current and resistance-based sensors are considered for the measurement of physical quantities such as temperature, pressure, strain, etc. Low resolution imaging sensors for robotic vision are also considered.

Analog-Digital Conversion↗

PubMed1993

Analogue synaptic noise--implications and learning improvements.

We analyse the effects of analogue noise on the synaptic arithmetic during multilayer perceptron training by expanding the cost function to include noise-mediated penalty terms. Predictions are made in the light of these calculations which suggest that fault tolerance, generalisation ability and learning trajectory should be improved by such noise-injection. Extensive simulation experiments on two distinct classification problems substantiate the claims. The results appear to be perfectly general for all training schemes where weights are adjusted incrementally, and have wide-ranging implications for all applications, particularly those involving "inaccurate" analogue neural VLSI.

Algorithms↗

PubMed1994

A constructive algorithm that converges for real-valued input patterns.

A constructive algorithm is presented which combines the architecture of Cascade Correlation and the training of perceptron-like hidden units with the specific error-correcting roles of Upstart. Convergence to zero errors is proved for any consistent classification of real-valued pattern vectors. Addition of one extra element to each pattern allows hyper-spherical decision regions and enables convergence on real-valued inputs for existing constructive algorithms. Simulations demonstrate robust convergence and economical construction of hidden units in the benchmark "N-bit parity" and "twin spirals" problems.

Algorithms↗

PubMed1995

Use of multilayer feedforward neural nets as a display method for multidimensional distributions.

We present a new method based on multilayer feedforward neural nets for displaying an n-dimensional distribution in a projected space of 1, 2 or 3 dimensions. A fully nonlinear net with several hidden layers is used. Efficient learning is achieved using multi-seed backpropagation. As a principal component analysis (PCA), the proposed method is useful for extracting information on the structure of the data set, but unlike the PCA, the transformation between the original distribution and the projected one is not restricted to be linear. Artificial examples and a real application are presented in order to show the reliability and potential of the method.

Artificial Intelligence↗

PubMed1997

Translation-, rotation-, scale-, and distortion-invariant object recognition through self-organization.

The task of visual object recognition is often complicated by the fact that a single 3-D object can undergo a number of transformations which can substantially alter its projection onto a 2-D surface, such as the retina. Such transformations include translation of the object in the visual field, changes in the size of the object, its orientation in the 2-D plane and the viewing perspective. For a general pattern recognition system to detect and recognize and object after such transformations, it must be able to associate widely differing patterns with the same object label. In this paper, a novel self-organizing model, called the Multiple Elastic Modules (MEM), is presented which attempts to solve this problem by searching a multi-dimensional space, where each axis is defined by one of the transformations (e.g. scale, translation, rotation, etc.). A particular object of a specific size, orientation and spatial location is mapped onto a single point in this space. Of course, distortions and minor variations in an object's image will expand this point to a small localized area in this multi-dimensional space. Such a powerful representation scheme comes at a cost of high computational demand due to the combinatorially large search space. The MEM approach to solving this problem efficiently partitions the solution space to search the most promising areas for the correct match. Simulation results are presented on detecting a stick-figure object under translation, distortion, scale, and rotation transformations in a cluttered background.

Algorithms↗

PubMed1997

Supervised adaptive Hamming net for classification of multiple-valued patterns.

A Supervised Adaptive Hamming Net (SAHN) is introduced for incremental learning of recognition categories in response to arbitrary sequences of multiple-valued or binary-valued input patterns. The binary-valued SAHN derived from the Adaptive Hamming Net (AHN) is functionally equivalent to a simplified ARTMAP, which is specifically designed to establish many-to-one mappings. The generalization to learning multiple-valued input patterns is achieved by incorporating multiple-valued logic into the AHN. In this paper, we examine some useful properties of learning in a P-valued SAHN. In particular, an upper bound is derived on the number of epochs required by the P-valued SAHN to learn a list of input-output pairs that is repeatedly presented to the architecture. Furthermore, we connect the P-valued SAHN with the binary-valued SAHN via the thermometer code.

Artificial Intelligence↗

PubMed1997

On neural blind separation with noise suppression and redundancy reduction.

Noise is an unavoidable factor in real sensor signals. We study how additive and convolutive noise can be reduced or even eliminated in the blind source separation (BSS) problem. Particular attention is paid to cases in which the number of sensors is larger than the number of sources. We propose various methods and associated adaptive learning algorithms for such an extended BSS problem. Performance and validity of the proposed approaches are demonstrated by extensive computer simulations.

Algorithms↗

PubMedDate not supplied

The prospects for analogue neural VLSI.

In recent years, the efforts of analogue, neural-hardware designers have shifted from generic analogue neurocomputers to "niche" markets in sensor fusion and robotics, and we explain why this is so. We describe the main differences between digital and analogue computation, and consider the advantages of pure analogue and pulsed methods of design. We then investigate some important issues in analogue design of neural machines, namely weight storage (volatile and non-volatile), on-chip learning, and arithmetic accuracy and its relationship to noise. Finally, we outline those areas in which analogue techniques are likely to prove most useful, and speculate as to their likely long-term utility.

Computers, Analog↗

PubMed1999

A self-organizing algorithm for vector quantizer design applied to signal processing.

Vector quantization plays an important role in many signal processing problems, such as speech/speaker recognition and signal compression. This paper presents an unsupervised algorithm for vector quantizer design. Although the proposed method is inspired in Kohonen learning, it does not incorporate the classical definition of topological neighborhood as an array of nodes. Simulations are carried out to compare the performance of the proposed algorithm, named SOA (self-organizing algorithm), to that of the traditional LBG (Linde-Buzo-Gray) algorithm. The authors present an evaluation concerning the codebook design for Gauss-Markov and Gaussian sources, since the theoretic optimal performance bounds for these sources, as described by Shannon's Rate-Distortion Theory, are known. In speech and image compression, SOA codebooks lead to reconstructed (vector-quantized) signals with better quality as compared to the ones obtained by using LBG codebooks. Additionally, the influence of the initial codebook in the algorithm performance is investigated and the algorithm ability to learn representative patterns is evaluated. In a speaker identification system, it is shown that the the codebooks designed by SOA lead to higher identification rates when compared to the ones designed by LBG.

Algorithms↗

PubMedDate not supplied

Cost analysis of PAPNET-assisted vs. conventional Pap smear evaluation in primary screening of cervical smears.

OBJECTIVE: To assess the difference in costs between PAPNET-assisted and conventional microscopy of cervical smears when used as a primary screening tool. STUDY DESIGN: We performed time measurements of the initial screening of smears by four cytotechnologists in one laboratory. Time was measured in 816 conventionally screened smears and in 614 smears with PAPNET-assisted screening. Data were collected on the components of initial screening, clerical activities and other activities in the total work time of cytotechnologists in the routine situation and on resource requirements for both techniques. RESULTS: PAPNET saved an average of 22% on initial screening time per smear. Due to costs of processing and additional equipment, the costs of PAPNET-assisted screening were estimated to be $2.85 (and at least $1.79) higher per smear than conventional microscopy. The difference in costs is sensitive to the rate of time saving, the possibility of saving on quality control procedures and the component of the initial screening time in the total work time of cytotechnologists. CONCLUSION: Although PAPNET is time saving as compared with conventional microscopy, the associated reduction in personnel costs is outweighed by the costs of scanning the slides and additional equipment. This conclusion holds under a variety of assumptions. Using PAPNET instead of conventional microscopy as a primary screening tool will make cervical cancer screening less cost-effective unless the costs of PAPNET are considerably reduced and its sensitivity and/or specificity are considerably improved.

Cost-Benefit Analysis↗

PubMed2002

Scalable hybrid computation with spikes.

We outline a hybrid analog-digital scheme for computing with three important features that enable it to scale to systems of large complexity: First, like digital computation, which uses several one-bit precise logical units to collectively compute a precise answer to a computation, the hybrid scheme uses several moderate-precision analog units to collectively compute a precise answer to a computation. Second, frequent discrete signal restoration of the analog information prevents analog noise and offset from degrading the computation. And, third, a state machine enables complex computations to be created using a sequence of elementary computations. A natural choice for implementing this hybrid scheme is one based on spikes because spike-count codes are digital, while spike-time codes are analog. We illustrate how spikes afford easy ways to implement all three components of scalable hybrid computation. First, as an important example of distributed analog computation, we show how spikes can create a distributed modular representation of an analog number by implementing digital carry interactions between spiking analog neurons. Second, we show how signal restoration may be performed by recursive spike-count quantization of spike-time codes. And, third, we use spikes from an analog dynamical system to trigger state transitions in a digital dynamical system, which reconfigures the analog dynamical system using a binary control vector; such feedback interactions between analog and digital dynamical systems create a hybrid state machine (HSM). The HSM extends and expands the concept of a digital finite-state-machine to the hybrid domain. We present experimental data from a two-neuron HSM on a chip that implements error-correcting analog-to-digital conversion with the concurrent use of spike-time and spike-count codes. We also present experimental data from silicon circuits that implement HSM-based pattern recognition using spike-time synchrony. We outline how HSMs may be used to perform learning, vector quantization, spike pattern recognition and generation, and how they may be reconfigured.

Action Potentials↗

PubMed2004

Adaptive two-pass median filter based on support vector machines for image restoration.

In this letter, a novel adaptive filter, the adaptive two-pass median (ATM) filter based on support vector machines (SVMs), is proposed to preserve more image details while effectively suppressing impulse noise for image restoration. The proposed filter is composed of a noise decision maker and two-pass median filters. Our new approach basically uses an SVM impulse detector to judge whether the input pixel is noise. If a pixel is detected as a corrupted pixel, the noise-free reduction median filter will be triggered to replace it. Otherwise, it remains unchanged. Then, to improve the quality of the restored image, a decision impulse filter is put to work in the second-pass filtering procedure. As for the noise suppressing both fixed-valued and random-valued impulses without degrading the quality of the fine details, the results of our extensive experiments demonstrate that the proposed filter outperforms earlier median-based filters in the literature. Our new filter also provides excellent robustness at various percentages of impulse noise.

Adaptation, Physiological↗

PubMed2001

Evolution of adaptive synapses: robots with fast adaptive behavior in new environments.

This paper is concerned with adaptation capabilities of evolved neural controllers. We propose to evolve mechanisms for parameter self-organization instead of evolving the parameters themselves. The method consists of encoding a set of local adaptation rules that synapses follow while the robot freely moves in the environment. In the experiments presented here, the performance of the robot is measured in environments that are different in significant ways from those used during evolution. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard fixed-weight controllers, that the method scales up well to large architectures, and that evolutionary adaptive controllers can adapt to environmental changes that involve new sensory characteristics (including transfer from simulation to reality and across different robotic platforms) and new spatial relationships.

Computer Simulation↗

PubMed1998

[Biological calculation methods and their application in pharmaceutical science].

This article gives an introduction to certain mathematical methods, that were developed with biological processes as model. Three methods are described: clustering and the more recently developed genetic algorithms and neural nets. Mainly the last two methods were applied first outside the medical and biological domain but are now used also in the medical and pharmaceutical sciences. There are many applications in the drug discovery field, but these methods are also becoming increasingly important in other domains of the pharmaceutical sciences (such as pharmaceutical technologies).

Algorithms↗