Search results for "NEURAL NETWORK"
showing 10 items of 1385 documents
Implementation of pattern recognition algorithm based on RBF neural network
2002
In this paper, we present implementations of a pattern recognition algorithm which uses a RBF (Radial Basis Function) neural network. Our aim is to elaborate a quite efficient system which realizes real time faces tracking and identity verification in natural video sequences. Hardware implementations have been realized on an embedded system developed by our laboratory. This system is based on a DSP (Digital Signal Processor) TMS320C6x. The optimization of implementations allow us to obtain a processing speed of 4.8 images (240x320 pixels) per second with a correct rate of 95% of faces tracking and identity verification.
Using Wave Propagation Simulations and Convolutional Neural Networks to Retrieve Thin Film Thickness from Hyperspectral Images
2021
Ill-posed inversion problems are one of the major challenges when there is a need to combine measurements with the theory and numerical model. In this study, we demonstrate the use of wave propagation simulations to train a convolutional neural network (CNN) for retrieving sub-wavelength thickness profiles of thin film coatings from hyperspectral images. The simulations are produced by solving numerically one-dimensional wave equation with a method based on Discrete Exterior Calculus (DEC). This approach provides a powerful tool to produce large sets of training data for the neural network. CNN was verified by simulated verification sets and measured reflectance spectra, both of which showe…
Capabilities of Ultrametric Automata with One, Two, and Three States
2016
Ultrametric automata use p-adic numbers to describe the random branching of the process of computation. Previous research has shown that ultrametric automata can have a significant decrease in computing complexity. In this paper we consider the languages that can be recognized by one-way ultrametric automata with one, two, and three states. We also show an example of a promise problem that can be solved by ultrametric integral automaton with three states.
On the Hierarchy Classes of Finite Ultrametric Automata
2015
This paper explores the language classes that arise with respect to the head count of a finite ultrametric automaton. First we prove that in the one-way setting there is a language that can be recognized by a one-head ultrametric finite automaton and cannot be recognized by any k-head non-deterministic finite automaton. Then we prove that in the two-way setting the class of languages recognized by ultrametric finite k-head automata is a proper subclass of the class of languages recognized by (k + 1)-head automata. Ultrametric finite automata are similar to probabilistic and quantum automata and have only just recently been introduced by Freivalds. We introduce ultrametric Turing machines an…
Dissimilarity Application in Digitized Mammographic Images Classification.
2006
Purpose of this work is the development of an automatic classification system which could be useful for radiologists in the investigation of breast cancer. The software has been designed in the framework of the MAGIC-5 collaboration. In the traditional way of learning from examples of objects the classifiers are built in a feature space. However, an alternative ways can be found by constructing decision rules on dissimilarity (distance) representations. In such a recognition process a new object is described by its distances to (a subset of) the training samples. The use of the dissimilarities is especially of interest when features are difficult to obtain or when they have a little discrim…
Potential implementation of reservoir computing models based on magnetic skyrmions
2018
Reservoir Computing is a type of recursive neural network commonly used for recognizing and predicting spatio-temporal events relying on a complex hierarchy of nested feedback loops to generate a memory functionality. The Reservoir Computing paradigm does not require any knowledge of the reservoir topology or node weights for training purposes and can therefore utilize naturally existing networks formed by a wide variety of physical processes. Most efforts prior to this have focused on utilizing memristor techniques to implement recursive neural networks. This paper examines the potential of skyrmion fabrics formed in magnets with broken inversion symmetry that may provide an attractive phy…
Theory of heterogeneous viscoelasticity
2015
We review a new theory of viscoelasticity of a glass-forming viscous liquid near and below the glass transition. In our model we assume that each point in the material has a specific viscosity, which varies randomly in space according to a fluctuating activation free energy. We include a Maxwellian elastic term and assume that the corresponding shear modulus fluctuates as well with the same distribution as that of the activation barriers. The model is solved in coherent-potential approximation (CPA), for which a derivation is given. The theory predicts an Arrhenius-type temperature dependence of the viscosity in the vanishing-frequency limit, independent of the distribution of the activatio…
The red tooth hypothesis: A computational model of predator-prey relations, protean escape behavior and sexual reproduction
2009
This paper presents an extension of the Red Queen Hypothesis (hereafter, RQH) that we call the Red Tooth Hypothesis (RTH). This hypothesis suggests that predator-prey relations may play a role in the maintenance of sexual reproduction in many higher animals. RTH is based on an interaction between learning on the part of predators and evolution on the part of prey. We present a simple predator-prey computer simulation that illustrates the effects of this interaction. This simulation suggests that the optimal escape strategy from the prey's standpoint would be to have a small number of highly reflexive, largely innate (and, therefore, very fast) escape patterns, but that would also be unlearn…
From the Golgi-Cajal mapping to the transmitter-based characterization of the neuronal networks leading to two modes of brain communication: Wiring a…
2007
After Golgi-Cajal mapped neural circuits, the discovery and mapping of the central monoamine neurons opened up for a new understanding of interneuronal communication by indicating that another form of communication exists. For instance, it was found that dopamine may be released as a prolactin inhibitory factor from the median eminence, indicating an alternative mode of dopamine communication in the brain. Subsequently, the analysis of the locus coeruleus noradrenaline neurons demonstrated a novel type of lower brainstem neuron that monosynaptically and globally innervated the entire CNS. Furthermore, the ascending raphe serotonin neuron systems were found to globally innervate the forebrai…
Diagnosis of Incipient Bearing Faults using Convolutional Neural Networks
2019
The majority of faults occurring in rotating electrical machinery is attributed to bearings. To reduce downtime, it is desired to apply various diagnostic methods so that bearing degradation can be detected in good time prior to a complete failure. The work presented in this paper utilizes a data-driven machine learning approach based on convolutional neural networks (CNNs) in order to diagnose different types of bearing faults. A one-dimensional CNN is trained on vibration signals and compared to a two-dimensional CNN trained in time-frequency domain using continuous wavelet transform (CWT). The proposed method is demonstrated on data collected from run-to-failure tests.The results show th…