PDF Results for "Neura Networks"

by RE Uhrig · 1991 · Cited by 14 — NEURAL NETWORKS AND THEIR. POTENTIAL APPLICATIONS TO NUCLEAR POWER PLANTS. Robert E. Uhrig. Department of Nuclear Engineering, University of Tennessee, ...11 p

by S Khastoo · 2020 · Cited by 4 — NeuRA significantly improves the efficiency of sampling in rate adaptation algorithms by using a neural network model to predict the expected throughput of many

by R Sharda · 1994 · Cited by 256 — Neural networks (NN) have been of interest to operations researchers and management science professionals since the early days of NN research. In.15 pages

by AF Armitage · 1995 · Cited by 16 — Neural networks in measurement and control. Dr. A.F. Armitage. Department ofElectrical, Electronic & Computing Engineering,. Napier University, Edinburgh.

Feb 4, 2016 — Artificial Neural Networks. Human and Artificial Neurons. Artificial Neurons. ANN Artchitecture. 3 Applications. 4 Case Study.90 pages

by P Maksud · 1998 · Cited by 23 — This study investigates the ability of artificial neural networks (ANN) to simultaneously correct for attenuation and Compton scattering in.

quantum neural networks - a burgeoning new field which integrates classical neurocomputing with quantum computation {I}. It is argued that the study of.23 pages

by DC Park · 1994 · Cited by 53 — The proposed BiLinear Recurrent Neural Network (BLRNN) is compared with Multilayer Perceptron. Neural Networks (MLPNN) for time series prediction problems. The 

by JC SPROTT · 1998 · Cited by 4 — Abstract╨Aesthetically appealing patterns are produced by the dynamical behavior of artificial neural networks with randomly chosen connection strengths.7 pag

by C PembrokeStreet · 1999 · Cited by 786 — 4. Neural Networks. A general methodof regression which avoids these difficulties is neural network analysis ...14 pages

by A ten BERG · Cited by 4 — hierarchically imposed evaluation functions will improve network accuracy and learning speed. Keywords: Neural Networks, Modularity, Hierarchy, ...

by SA Harp · Cited by 168 — We present a general and systematic method for neural network design based on the genetic algorithm. The technique works in conjunction with network learning ...

by A Labatie · 2018 · Cited by 8 — characterizing neural networks at that time can be seen as characterizing the hypothesis space of input-output map- pings that will be favored or reachable ...

by A Stafylopatis · Cited by 1 — As a first approach we develop a random neural network model, based upon simple probabi- listic assumptions, whose organization is studied by means of dis-.10 page

by J Barhen · Cited by 17 — O(N2), where N is the number of neurons in the network. 1 INTRODUCTION. The biggest promise of artifcial neural networks as computational tools lies in the hope ...11

by D Barschdorff · 1991 · Cited by 81 — paper gives a summary of known neural networks applications ... artificial neural network structures and learning algorithms is.19 pages

Abstract. The Vapnik-Chervonenkis dimension has proven to be of great use in the theoretical study of generalization in artificial neural networks.

by J Yang · 2014 · Cited by 12 — Over the past several decades, neural networks have evolved into powerful computation systems, which are able to learn complex nonlinear input-output ...

by L Zhou · Cited by 2 — Besides remote sensing and artificial neural networks, GIS can be helpful for the study of urban growth and landscape changes. GIS-based spatial analysis and ...154 pages

by L Francis · Cited by 34 — fraud data and will compare its performance to that of neural networks. Acknowledgements: The author thanks the Automobile Insurers Bureau of Massachusetts ...37 page

by T Kolarik · 1994 · Cited by 127 — neural networks are suitable for many tasks in pattern recognition and machine learning. In this pa- per we present an APL system for forecasting univari-.

by M Kahng · 2018 · Cited by 246 — This idea has been extended to the case of deep neural networks. Karpathy [18] visualized the activations for each layer of a neural network on his website.

Mar 22, 2021 — Neural Networks: Basic Methods and. Applications in Finance, Management and. Decision Making, a Roadmap Nov Res Sci. 6(5). NRS. 000648.2021.

2016 lectures: CS 231: Convolutional Neural Networks for. Visual Recognition by Fei-Fei Li, Andrej Karpathy and Justin. Johnson. Reading List ...

by F Dehbozorgi · 2012 · Cited by 10 — (six and four weather parameters) to artificial neural networks (ANNs) were ... The most commonly identified training algorithm of a neural network is the.

by A Labatie · 2019 · Cited by 8 — We identify the multiplicativity of layer composition as the driving force towards pathologies in feedforward networks: either with the neural network hav- ingÂ

by T Davies · Cited by 3 — 1 Features of Neural Networks and. Knowledge-Based Systems. Attempts to build intelligent machines have historically di- vided into two broad types.

Graph Neural Networks. Jure Leskovec, Stanford University. Inductive Representation Learning on Large Graphs. W. Hamilton, R. Ying, J. Leskovec.

by RM Wambua · 2014 · Cited by 15 — Citation: Wambua RM, Mutua BM, Raude JM (2014) Drought Forecasting Using Indices and Artificial Neural Networks for Upper Tana River Basin,.

Pyrolysis mass spectra of a virgin olive oil (a) adulterated with 5 o/o soya oil (b). PyMS and artificial neural networks constitutes a powerful approach to the ...

Biological neural networks are highly recurrently connected, and many authors have studied recurrent network models of various types of percep- tual and memory ...

Neural Networks. Algorithms, Applications, and Programming Techniques. James A. Freeman. David M. Skapura. Loral Space Information Systems and.

by MS Unluturk · Cited by 9 — Deconvolution Neural Network (DNN), the second method is. (ADNN), and the third method is refered to as the htabilistic. Deconvolution Neural Network (PDNN) ...

by M Aiken · 2000 · Cited by 6 — search has been devoted to how artificial neural networks may improve these ... per shows how a neural network may be used to forecast GDP in the United ...

by AJ Meade — project was a feasibility study on the use of artificial neural networks (ANN) in experimental data acquisition and tile design of aerodynamic components.

by JT Hancock · 2020 · Cited by 58 — the training of a neural network, but rather take the form of more involved pre-pro- cessing of data. Automatic techniques employ machine learning algorithms

by M Withnall · 2020 · Cited by 38 — Efforts have also been taken to enable neural networks to do representation learning, i.e. the neural network is able to learn descriptors itself instead of 

by FJ Veredas · 2004 · Cited by 6 — A new computational approach to study correlated neural activity is presented. Simulating Elementary Neural NEtworks for Correlation.

by JM Barroso-Maldonado · 2017 · Cited by 3 — COMPRESSOR USING ARTIFICIAL NEURAL NETWORKS AND PROBABILISTIC. NEURAL NETWORKS ... an artificial neural network that controls the system.

Arthur J. Decker, "Neural networks for calibration tomography," Proc. SPIE. 2005, Optical Diagnostics in Fluid and Thermal Flow, (2 December 1993);.

by P Kraipeerapun · 2009 · Cited by 1 — Applying Complementary Neural Networks to. Porosity Prediction in Well Log Data Analysis. Paw alai Kraipeerapun*, Chun Che Fung t, Sathit Nakkrasae*, ...

by G Baud-Bovy · 1992 — This thesis explores using Artificial Neural Network (ANN) technology instead ... The ability of artificial neural networks to perform well on noisy data ...

by BW Dickinson · 1991 — neural networks containing feedback (trellis-structured networks in one particular ... feedforward (SHLFF) neural networks has only very recently been ...

Oct 9, 2017 — This paper reports the use of artificial neural networks (ANN) approach to predict nickel concentration in external.

Neural Networks. Algorithms, Applications, and Programming Techniques. James A. Freeman. David M. Skapura. Loral Space Information Systems and.

by CS Chen · 2012 · Cited by 42 — artificial neural networks (ANN). 1. Introduction. The purpose of a wireless location identification algorithm is to estimate the position ...

bines convolutional neural network character recognizers with graph-based stochastic models ... Neural Networks and Recurrent Neural Networks can handle.

by SM Morosohk · 2021 · Cited by 1 — Neural networks. NUBEAM. A B S T R A C T. A neural network model of the effects of neutral beam injection on DIII-D has been developed.

systems available using Artificial Neural Networks (ANN's) as an Intelligent. Agent for Intrusion Detection. This Paper focuses how inputs can be.

Joint Conference on Neural Networks (IJCNN) held virtually, as part of the IEEE World Congress on. Computational Intelligence (IEEE WCCI) 2020.

by D PIETROW · 2018 · Cited by 31 — Key words: Neural networks, detection, recognition, drones. 1. Introduction. Image recognition and detection is a complex process that demands a lot of ...

An artificial neural network consists of processing units, organized in lavers of units (also referred to as artificial neurons). Training of an ANN is done ...

by WH Hsu · 1997 — neural networks (ANNs) with symbolic machine learning methods in a probabilistic reasoning framework. Improved understanding of the semantics of neural nets ...

by R Kulkarni · 2016 · Cited by 3 — A neural network that expresses competition amongst output neurons with lateral ... and generalization be implemented in standard, vanilla neural networks?

by S Zhang — Based on Bidirectional Gated Recurrent Unit networks and Capsule ... neural network (CNN) and Recurrent Neural Network results in the loss ...

by Δ Μαδυτινός · 2004 — key words: Neural networks, forecasting, finance. Dimitrios Maditinos. Applications Professor. ΤΕΙ of Kaνala. Department of Business. Administration.

by WW Cushing Jr · 1997 · Cited by 4 — Neura! networks simulate the behavior oí the nervous systems in the learning process. A neural network can be described through its characteristics.

Mar 10, 2020 — Many types of neural networks have been pro- posed and studied in the literature and the Hopfield-type network has be- come an important one due ...

Sep 16, 1995 — (ARPA) Artificial Neural Network (ANN) technology program. ... Artificial Neural Networks (ANNs) is being assessed through high-impact ...

by S Valdivia · 2016 · Cited by 5 — This study applies a neural network (NN) methodology to determine the relative variable impact between variables, established by financial theory, ...

by JM Szumega · 2021 · Cited by 1 — Artificial neural networks. Machine learning. System-on-chip. FPGA. A B S T R A C T. The European Organization for Nuclear Research (CERN) ...

by A Dutta · 2019 · Cited by 27 — An Efficient Convolutional Neural Network for Coronary Heart Disease Prediction. Aniruddha Dutta1, 2, Tamal Batabyal3,6, Meheli Basu4, Scott T. Acton3, 5.

Aug 17, 2017 — Explosion Using MLP and RBF Neural Networks ... Recent developments of the neural network classifiers indicate that they are useful for ...

by O Moselhi · 1991 · Cited by 268 — Expert systems, robotics, and neural networks are among current artificial intelligence (AI) research areas of interest to the construction industry. On.

by RA Cottis · Cited by 59 — Neural networks, for all their intrinsic appcat, ,are mIt without their Iimitat ions. ... [Jsed without caution, a neural network can give answers.

Abstract: . This paper proposes an approach for recognizing human faces. The face detection technique is implemented using artificial neural network, ...

by S Robertson · Cited by 12 — Artificial neural networks for age estimation. Marine and Freshwater Resources Institute v. List of Figures. Figure 1. Sectioned King George whiting otolith ...

by AJ Dautel · 2020 · Cited by 5 — Keywords Deep learning · Financial time series forecasting · Recurrent neural networks · Foreign exchange rates. JEL Classification C14 · C22 · C45.

by S Piramuthu · 2012 — Recent years have seen the growth in popularity of using neural networks in ... tions of neural networks in a variety of financial applications including ...

by S MITRA — NEURAL NETWORKS AT THE INPUT, OUTPUT AND. NEURONAL LEVELS. SUSHMITA MITRA AND SANKAR K. PAL. Machine Intefligence Un ii, Indian Statislical institute.

by D Guyot · 2019 · Cited by 10 — artificial neural network, building retrofit, control optimization, energy consumption prediction, machine learning, predictive control.

by IS Fernandez — Convolutional neural networks. Deep learning. Magnetic resonance imaging. Pediatric. A B S T R A C T. Objective: To develop and test a deep ...

This paper explores the applicability of neural networks (NN) for forecasting meteotsuna- mis affecting Ciutadella harbour (Menorca, Balearic Islands, ...

by JA Walter · 1993 · Cited by 267 — Implementation of Self-Organizing Neural Networks for Visuo-Motor Control of an Industrial Robot. Jörg A. Walter and Klaus J. Schulten. Abstract.

by S Draghici · Cited by 1 — VLSI friendly neural network used in classification problems. A VLSI-friendly neural network is a neural network using exclusively integer weights in a.

Aug 28, 2015 — patent is extended or adjusted under 35 neural networks,' Advances in neural ... the input image, wherein the deep neural network comprises.

by RP de Lima · 2020 · Cited by 9 — To address this challenge, we explore the use of deep convolutional neural networks (CNN) as a tool for acceleration and automatization of ...

by AS Ogilvie · Cited by 1 — This thesis summarizes an investigation of the application of neural network (NN) con- trol to a commercial robot. It presents the resdts of simulations and ...

by LA Francis · 2003 · Cited by 1 — Neural Networks in Insurance. Louise A. Francis. The chapter will provide a basic introduction to the use of neural networks as an analytical modeling tool ..

by W Utschick · Cited by 4 — ABSTRACT. An extension of a feedforward neural network is presen- ted. Although utilizing linear threshold functions and a.

by A Kellner · Cited by 21 — CNNA-94 Third IEEE International Workshop on Cellular Neural Networks and ... The Discrete-Time Cellular Neural Network (DTCNN) [l] is a discrete-time, ...

Neural net and back-prop algorithm – Ch.6. • Train a deep net – Ch.8 ... Recurrent neural net (RNN) for modelling sequence ... Feed-forward neural network.

previously proposed algorithms which extract symbolic rules from neural networks. First, we train a network where each input of the data can only have one ...

by B Bart · 2001 — Neural Networks, Rule Extraction, Credit Scoring. In the field of credit scoring, ... neura, network rule extraction techniques, Neurolinear,.

by K Shihano — In this paper we present a Time Delay Neural Network (TO.'N) approach to phoneme recognition which is characteriaed ... 2 Time Delay Neural Networks (TDNN).

by S Vallabhan · 1995 · Cited by 1 — Applicati on ofArtificial Neural Networks for Voltage Stability ... Significance of Artificial Neural Networks in Modem Power System Control.

Key words: Demand forecasting, artificial neural networks, metal-mechanical industry, production planning, industry, artificial intelligence. INTRODUCTION.

BiDirectional Neura! Networks (BDNN) are based on Multi Layer Perceptrons trained by the error back-propagation algorithm.

Keywords: - Artificial Neural Network, Classification Accuracy, Daubechies, EEG, Wavelet, and Entropy. 1 Introduction. Epilepsy is one of the most common ...

by DM Atia · 2011 · Cited by 2 — Keywords:Aquaculture, Forced Circulation Hot Water System, Artificial Neural Networks. 1. Introduction. The shrimp farming is an important economical ...

May 10, 2021 — Machine learning based artificial neural networking (ANN) has been acknowledged to be ... been stated that artificial neural network (ANN).

by P Ntourntoufis · Cited by 2 — SeIf-organising weightless neural networks and unsupervised learning ... This thesis is concerned with Weightless Artificial Neural Networks (WANNs). The.

Jun 16, 2020 — artificial neural networks, migraine, supervised learning, automatic classification techniques. Open Peer Review. Reviewer Status.

by Y Yin · 2021 · Cited by 2 — RANDOM NEURAL NETWORK METHODS AND DEEP. LEARNING. YONGHUA YIN. Intelligent Systems and Networks Group Department of Electrical and Electronic Engineering ...

by O Tarkhaneh · 2019 · Cited by 12 — feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search.

development of neural networks provides evidence that "pioneering" ... A further investigation of institutional differences among neural network scientists.

by K Dobs · Cited by 6 — convolutional neural networks (CNNs) to test whether models optimized to recognize faces and objects require functional segregation for each task.

by HK ALMEJRAB · 2018 — Recently, neural networks have shown a great use in prediction ... Keywords: Artificial neural network; Solar radiation; Backpropagation; Radial basis.

by JM Vitek · 1999 · Cited by 17 — shownthat the neura[ network wasconsiderably moreaccu!ate than other currently available methods. KEYWORDS:neural networks; weld pool shape; Iaser welds; ...

[12] Telgarsky, Benefits of depth in neural networks. COLT 2016. [13] Bölcskei, Grohs, Kutyniok, Petersen. Memory-optimal neural network approximation. Wavelets ...