Accurate modeling of SiGe HBT using artificial neural networks: Performance Comparison of the MLP and RBF Networks

Size: px
Start display at page:

Download "Accurate modeling of SiGe HBT using artificial neural networks: Performance Comparison of the MLP and RBF Networks"

Transcription

1 Accurate modeling of SiGe HBT using artificial neural networks: Performance Comparison of the MLP and RBF etworks Malek Amiri Abdeboochali Department of Electrical Engineering Razi University Kermanshah, Iran Mohammad M. Karkhanechi Department of Electrical Engineering Razi University Kermanshah, Iran Abstract In this paper, we compare different architectures of Multi-Layer Perception (MLP) and radial basis function (RBF) neural networks for modeling of silicon-germanium (SiGe) heterounction bipolar transistors (HBTs). Model has been trained and tested with different sets of input/output data. Accuracy of the model is examined for all the DC and S parameters in a wide range of bias and frequencies. First, different architectures of the MLP and RBF are created to determine the best topology and training algorithm in term of accuracy. Then, the performance of best configuration of the MLP and RBF is compared. umerous simulation results in the paper demonstrate that the RBF provides much better performance than MLP neural networks when it comes to this type of modeling. Keywords- SiGe HBT; eural networks; modeling. I. ITRODUCTIO Heterounction Bipolar Transistors (HBTs) have become very useful devices for different applications at the microwave and millimeter-wave frequencies. HBT technology is considered as very appropriate for RF front-end circuits in next-generation wireless communications [1]. In recent years, the SiGe hetero-unction bipolar devices (HBTs) have obtained great importance due to their good noise and high frequency (HF) performance. Due to remarkable capabilities of artificial neural networks (As) such as generalization, parallel processing, nonlinear system modeling, adaptation and function approximating, As have been extensively studied and applied in a wide array of contexts [2]-[3]-[4]. The most important feature of neural models is their ability to generalize, i.e. The correct answer even for input values not used during the A training process provides. In that way, the developed models can be used for a reliable prediction over a wide range of input parameters. eural networks have been applied in microwave nonlinear device modeling and noise modeling of SiGe HBT s [5]-[6]. In this paper we study different architectures of MLP and RBF neural networks to find the network which is the best for modeling SiGe HBT DC and S parameters. The overall model architecture is composed of 9 artificial neural network (A), among which one take care of the DC fitting and the rest are for modeling the RF behavior. The inputs for the DC output (collector current) are dc collector-emitter voltage (V ce ), dc base current (I b ) and those corresponding to the RF outputs (real and imaginary part of S parameters) are the frequencies in addition to the dc collector-emitter voltage and dc base current. A simplified overview of the proposed A model is shown in Fig. 1. The rest of the paper is organized as follows: The following section gives a brief insight of the multilayer perceptron neural network. In Section III, a brief description of the radial basis function neural network is given. The DC and RF modeling using A and the corresponding results, and discussions are followed in the next section. II. THE MLP The schematic diagram of an MLP illustrated in Fig. 2. In the conventional structure of an MLP, a neuron receives its Figure 1. A simplified overview of the proposed A model for DC and S parameters modeling of SiGe HBT.

2 radial activation function (a nonlinear transfer function) and each output unit implements a weighted sum of hidden units outputs. The structure of the RBF network is shown in Fig. 3. The output of ith neuron in the output layer of the RBF network is determined as follows: M y ( x) w x c ; i 1 m i i,..., 1 Figure 2. The MLP structure. input either from other neurons or from external inputs (input vector). A weighted sum of these inputs constitutes the argument of a nonlinear activation function. The resulting value of the activation function is the neural output. In this structure, the weights correspond to the synapses in a biological neuron, while the activation function is associated with the intracellular current conduction mechanism in the soma. An artificial neuron is an oversimplified but useful approximation of the biological neuron. This simple model ignores many of the characteristics of its biological counterpart, e.g. it does not take into account the time delays that affect the dynamics of the system [7]. In Fig. 2, the output Y of the MLP is a vector with n components determined in the terms of m components of an input vector X and l components of the hidden layer. The mathematical representation may be expressed as: l m yi vi g w k xk bw bvi i 1,..., n 1 k1 Where (.) is the basis function which is described using x c, c is the center vector for hidden neuron and w i is the weight between the node of the hidden layer and the node i of the output layer, m is the number of nodes in the output layer. The norm is typically taken to be the Euclidean distance and the basis function is taken to be Gaussian: c 2 x c x exp 2 2 Where is the width parameter of the th hidden unit in the hidden layer [7]. In an RBF network there are three types of parameters that need to be chosen to adapt the network for a particular task: the center vectors c, the output weights w i, and the RBF width parameters. In this way, the training process is usually divided into two steps: First, the center and width parameters of the hidden layer are determined using only the input data set and by utilizing unsupervised training algorithm such as K-means [9], decision trees [10] and self-organizing feature maps [11]. Second, the output weights (connecting the hidden layer with the output layer) are determined using both input and output data and by Singular Value Decomposition (SVD) or Least Mean Squared (LMS) algorithms [12]. Both steps are relatively fast when compared to back-propagation training algorithm. The number of basis functions controls the Where v i and w k are synaptic weights, x k is k th element of the input vector, g(.) is an activation function and b is the bias which has the effect of increasing or decreasing the net input of the activation function depending on whether it is positive or negative, respectively. It has been shown that the MLP with a tanh nonlinearity or other monotonic nonlinearities is a universal approximator to any arbitrary input-output mappings provided that some reasonable conditions on the nonlinear mapping are satisfied [8]. III. THE RBF Radial basis function neural networks are special classes of the feed-forward neural network models. RBF network is a three-layer network, where each hidden unit implements a Figure 3. The RBF architcture.

3 complexity and the generalization ability of the RBF network. RBF networks with too few basis functions can not fit the training data adequately due to limited flexibility. I. SIMULATIO RESULTS AD DISCUSSIO In order to train an A model, the most common approach is to divide the data samples collected from experiments into two groups, the training and validation data sets. The training group is used to train the A model by adusting the weight matrices of the network model. The validation group is used to ensure that the A has properly learned the relationship between inputs and outputs and has been able to generalize the results. This data set should include samples which are not included in the training data set. This method is suitable when there are enough data samples to train the neural network. In this section, the DC and S parameters modeling of SiGe HBT will be presented. The DC modeling is done in the wide range of Vce (0 to 5 V), Ib (25 to 125μA) and RF modeling is done in the frequency range (0.1 to 40 GHz), Vce (2 and 6 V) and Ib (10μA). The DC and S parameters values used for the training data are taken from advanced design system (ADS) software. For the SiGe HBT, Vertical Bipolar Inter Company (VBIC) model into ADS simulation is used [13]. Each of the DC network and eight RF networks are trained using 380 and 302 samples of simulated data, respectively. Different sets of 125 and 100 input/output simulated samples were used as test data for validating the DC and RF behavior, respectively. The test and training data samples should be different and are selected randomly from the original database (ADS). We used MATLAB to train the A model. To decide the best network in the accuracy test we used the mean relative error (MRE%) and the average error (AE%) to compare the accuracy of these networks. for testing data set, where the relative error for variable X is given by: RE% x (sim) (pred) 100 x x (sim) where sim and pred stand for ADS simulation (the actual values) and the predicted values, respectively. Also, the Mean Relative Error is given by: TABLE I. DC/RF Prediction THE MEA RELATIVE ERROR AD AVERAGE ERROR FOR MLP MODEL WITH TEST DATA Several proposed multilayer perceptron (MLP) network configuration with different number of neurons in two hidden layer were trained using the training set. The number of neurons for each hidden layer were in the range of On the basis of two above-mentioned criteria, the MLP model with structure (i.e., two neurons in the input layer, eleven neurons in the first hidden layer, nine neurons in the second hidden layer and one neuron in the output layer) for DC modeling and, the MLP model with structure for RF modeling were selected as the best model. Gaussian basis functions with constant smoothing parameters were used for the RBF. After several trial-anderror simulations and to improve generalization, we selected σ=0.2 for RBF network. It is noted that training processes in RBF use optimized number of hidden neurons that in turn allow for efficient approximation of the mapping function between the input and output spaces. In this technique, neurons are added to the network until the sum-squared error falls beneath an error goal or a maximum number of neurons have been reached. Based on the accuracy test results that are shown in table I and table II it is clear that RBF network has better accuracy to model SiGe HBT DC and S parameters. The accuracy for RBF network is also shown graphically in Figs. 4-8, where the DC and S parameters, obtained by the ADS simulation and A model (RBFn) for bias points outside of training set i.e., test set are presented. TABLE II. Test error DC/RF Test error MRE% AE% Prediction MRE% AE% Re(S 11) Im(S 11) Re(S 12) Im(S 12) Re(S 21) Im(S 21) Re(S 22) Im(S 22) I c THE MEA RELATIVE ERROR AD AVERAGE ERROR FOR RBF MODEL WITH TEST DATA 1 x(sim) x(pred) MRE% 100 x i 1 (sim) DC/RF Prediction Test error DC/RF Test error MRE% AE% Prediction MRE% AE% Re(S 11) Im(S 11) where is the number of points. The average error for variable X is given by: 1 AE% 100 x ( sim) x(pred) i1 Re(S 12) Im(S 12) Re(S 21) Im(S 21) Re(S 22) Im(S 22) I c The results proved that RBF networks have a good performance for noise modeling of SiGe HBT s.

4 Figure 4. Current voltage characteristics curve (I c-v ce) for SiGe HBT using ADS (line) and A (scattered). Figure 7. Plot of ADS simulation and A model of S 11 and S 21 for V ce=6v Figure 5. Plot of ADS simulation and A model of S 11 and S 21 for V ce=2v Figure 8. Plot of ADS simulation and A model of S 12 and S 22 for V ce=6v REFERECES [1] Z. Marinković, A. Stosić, V. Markovic, and O. Pronic, As in Bias- Dependent Modeling of S-parameters of Microwave FETs and HBTs, Microwave Review, pp , June [2] M. Amiri, H. Davandeh, A. Sadeghian, and S. Chartier, Feedback associative memory based on a new hybrid model of generalized regression and self-feedback neural networks, eural etworks, 23(7), pp , [3] M. Amiri, M. B. Menha, and M. J. Yazdanpanah, A eural-etwork- Based Controller for a Single-Link Flexible Manipulator: Comparison of FF and DR Controllers, IJC, IEEE, pp , Hong Kong, [4] M. Amiri, A.Sadeghian, and S. Chartier, One-shot training algorithm for self feedback neural networks, Annual Conference of the orth American Fuzzy Information Processing Society - AFIPS, no , Toronto, Canada, Figure 6. Plot of ADS simulation and A model of S 12 and S 22 for V ce=2v

5 [5] X. Li, J. Gao, and G. Boeck, Microwave nonlinear device modeling by using an artificial neural network, Semicond. Sci. Technol, vol. 21, pp , [6] A. Stosić, Z. Marinković, and V. Marković, eural etwork for oise Modeling of SiGe HBT S, Journal of Automatic Control, University of Belgrade, vol. 16, pp , [7] M. Amiri, M. Rafienia, and A. Sadeghian, Estimation of betamethasone release profiles from an in situ forming system based on the biodegradable polymer using artificial neural networks, IFMBE Proceedings, pp , Germany, [8] T. Chen, and H. Chen, Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical system, IEEE Trans, eural etworks 6, pp , [9] J. Moody, and C. Darken, Fast Learning etworks of Locally-Tuned Processing Units, eural Computation, pp , [10] M. Kubat, Decision Trees Can Initialize Radial-Basis Function etworks, IEEE Transactions, eural etworks, pp , [11] J. Robert, and L.C.J. Hewlett, Radial Basis Function etworks 2, ew Advances in Design, [12] Yu. Bing, and He. Xingshi, Training Radial Basis Function etworks with Differential Evolution, Proceedings of World Academi of Science, Engineering and Technology, 11, ISS, pp , [13] A. Chakravorty, R. Garg, and C. K. Maiti, Comparison of state-of-theart bipolar compact models for SiGe-HBTs, Applied Surface Science, vol. 224, pp , 2004.

CSE 5526: Introduction to Neural Networks Radial Basis Function (RBF) Networks

CSE 5526: Introduction to Neural Networks Radial Basis Function (RBF) Networks CSE 5526: Introduction to Neural Networks Radial Basis Function (RBF) Networks Part IV 1 Function approximation MLP is both a pattern classifier and a function approximator As a function approximator,

More information

Channel Performance Improvement through FF and RBF Neural Network based Equalization

Channel Performance Improvement through FF and RBF Neural Network based Equalization Channel Performance Improvement through FF and RBF Neural Network based Equalization Manish Mahajan 1, Deepak Pancholi 2, A.C. Tiwari 3 Research Scholar 1, Asst. Professor 2, Professor 3 Lakshmi Narain

More information

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

COMPUTATIONAL INTELLIGENCE

COMPUTATIONAL INTELLIGENCE COMPUTATIONAL INTELLIGENCE Radial Basis Function Networks Adrian Horzyk Preface Radial Basis Function Networks (RBFN) are a kind of artificial neural networks that use radial basis functions (RBF) as activation

More information

CHAPTER IX Radial Basis Function Networks

CHAPTER IX Radial Basis Function Networks CHAPTER IX Radial Basis Function Networks Radial basis function (RBF) networks are feed-forward networks trained using a supervised training algorithm. They are typically configured with a single hidden

More information

Neural Network Learning. Today s Lecture. Continuation of Neural Networks. Artificial Neural Networks. Lecture 24: Learning 3. Victor R.

Neural Network Learning. Today s Lecture. Continuation of Neural Networks. Artificial Neural Networks. Lecture 24: Learning 3. Victor R. Lecture 24: Learning 3 Victor R. Lesser CMPSCI 683 Fall 2010 Today s Lecture Continuation of Neural Networks Artificial Neural Networks Compose of nodes/units connected by links Each link has a numeric

More information

Image Compression: An Artificial Neural Network Approach

Image Compression: An Artificial Neural Network Approach Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and

More information

Global Journal of Engineering Science and Research Management

Global Journal of Engineering Science and Research Management A NOVEL HYBRID APPROACH FOR PREDICTION OF MISSING VALUES IN NUMERIC DATASET V.B.Kamble* 1, S.N.Deshmukh 2 * 1 Department of Computer Science and Engineering, P.E.S. College of Engineering, Aurangabad.

More information

Research on the New Image De-Noising Methodology Based on Neural Network and HMM-Hidden Markov Models

Research on the New Image De-Noising Methodology Based on Neural Network and HMM-Hidden Markov Models Research on the New Image De-Noising Methodology Based on Neural Network and HMM-Hidden Markov Models Wenzhun Huang 1, a and Xinxin Xie 1, b 1 School of Information Engineering, Xijing University, Xi an

More information

Prior Knowledge Input Method In Device Modeling

Prior Knowledge Input Method In Device Modeling Turk J Elec Engin, VOL.13, NO.1 2005, c TÜBİTAK Prior Knowledge Input Method In Device Modeling Serdar HEKİMHAN, Serdar MENEKAY, N. Serap ŞENGÖR İstanbul Technical University, Faculty of Electrical & Electronics

More information

Radial Basis Function Neural Network Classifier

Radial Basis Function Neural Network Classifier Recognition of Unconstrained Handwritten Numerals by a Radial Basis Function Neural Network Classifier Hwang, Young-Sup and Bang, Sung-Yang Department of Computer Science & Engineering Pohang University

More information

Radial Basis Function Networks

Radial Basis Function Networks Radial Basis Function Networks As we have seen, one of the most common types of neural network is the multi-layer perceptron It does, however, have various disadvantages, including the slow speed in learning

More information

Dynamic Analysis of Structures Using Neural Networks

Dynamic Analysis of Structures Using Neural Networks Dynamic Analysis of Structures Using Neural Networks Alireza Lavaei Academic member, Islamic Azad University, Boroujerd Branch, Iran Alireza Lohrasbi Academic member, Islamic Azad University, Boroujerd

More information

Simulation of Back Propagation Neural Network for Iris Flower Classification

Simulation of Back Propagation Neural Network for Iris Flower Classification American Journal of Engineering Research (AJER) e-issn: 2320-0847 p-issn : 2320-0936 Volume-6, Issue-1, pp-200-205 www.ajer.org Research Paper Open Access Simulation of Back Propagation Neural Network

More information

Width optimization of the Gaussian kernels in Radial Basis Function Networks

Width optimization of the Gaussian kernels in Radial Basis Function Networks ESANN' proceedings - European Symposium on Artificial Neural Networks Bruges (Belgium), - April, d-side publi., ISBN -97--, pp. - Width optimization of the Gaussian kernels in Radial Basis Function Networks

More information

Research on Evaluation Method of Product Style Semantics Based on Neural Network

Research on Evaluation Method of Product Style Semantics Based on Neural Network Research Journal of Applied Sciences, Engineering and Technology 6(23): 4330-4335, 2013 ISSN: 2040-7459; e-issn: 2040-7467 Maxwell Scientific Organization, 2013 Submitted: September 28, 2012 Accepted:

More information

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of

More information

DEVELOPMENT OF NEURAL NETWORK TRAINING METHODOLOGY FOR MODELING NONLINEAR SYSTEMS WITH APPLICATION TO THE PREDICTION OF THE REFRACTIVE INDEX

DEVELOPMENT OF NEURAL NETWORK TRAINING METHODOLOGY FOR MODELING NONLINEAR SYSTEMS WITH APPLICATION TO THE PREDICTION OF THE REFRACTIVE INDEX DEVELOPMENT OF NEURAL NETWORK TRAINING METHODOLOGY FOR MODELING NONLINEAR SYSTEMS WITH APPLICATION TO THE PREDICTION OF THE REFRACTIVE INDEX THESIS CHONDRODIMA EVANGELIA Supervisor: Dr. Alex Alexandridis,

More information

Department of Electronics and Telecommunication Engineering 1 PG Student, JSPM s Imperial College of Engineering and Research, Pune (M.H.

Department of Electronics and Telecommunication Engineering 1 PG Student, JSPM s Imperial College of Engineering and Research, Pune (M.H. Volume 5, Issue 4, 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Introduction to Probabilistic

More information

Comparative Analysis of Multi-layer Perceptron and Radial Basis Function for Contents Based Image Retrieval

Comparative Analysis of Multi-layer Perceptron and Radial Basis Function for Contents Based Image Retrieval Comparative Analysis of Multi-layer Perceptron and Radial Basis Function for Contents Based Image Retrieval Monis Ahmed Thakur 1, Syed Saad Hussain,Kamran Raza 3, Manzoor Hashmani 4 Faculty of Engineering,

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

Research Article International Journals of Advanced Research in Computer Science and Software Engineering ISSN: X (Volume-7, Issue-6)

Research Article International Journals of Advanced Research in Computer Science and Software Engineering ISSN: X (Volume-7, Issue-6) International Journals of Advanced Research in Computer Science and Software Engineering Research Article June 17 Artificial Neural Network in Classification A Comparison Dr. J. Jegathesh Amalraj * Assistant

More information

For Monday. Read chapter 18, sections Homework:

For Monday. Read chapter 18, sections Homework: For Monday Read chapter 18, sections 10-12 The material in section 8 and 9 is interesting, but we won t take time to cover it this semester Homework: Chapter 18, exercise 25 a-b Program 4 Model Neuron

More information

IMPLEMENTATION OF RBF TYPE NETWORKS BY SIGMOIDAL FEEDFORWARD NEURAL NETWORKS

IMPLEMENTATION OF RBF TYPE NETWORKS BY SIGMOIDAL FEEDFORWARD NEURAL NETWORKS IMPLEMENTATION OF RBF TYPE NETWORKS BY SIGMOIDAL FEEDFORWARD NEURAL NETWORKS BOGDAN M.WILAMOWSKI University of Wyoming RICHARD C. JAEGER Auburn University ABSTRACT: It is shown that by introducing special

More information

TWRBF Transductive RBF Neural Network with Weighted Data Normalization

TWRBF Transductive RBF Neural Network with Weighted Data Normalization TWRBF Transductive RBF eural etwork with Weighted Data ormalization Qun Song and ikola Kasabov Knowledge Engineering & Discovery Research Institute Auckland University of Technology Private Bag 9006, Auckland

More information

4.12 Generalization. In back-propagation learning, as many training examples as possible are typically used.

4.12 Generalization. In back-propagation learning, as many training examples as possible are typically used. 1 4.12 Generalization In back-propagation learning, as many training examples as possible are typically used. It is hoped that the network so designed generalizes well. A network generalizes well when

More information

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,

More information

Face Detection Using Radial Basis Function Neural Networks With Fixed Spread Value

Face Detection Using Radial Basis Function Neural Networks With Fixed Spread Value Detection Using Radial Basis Function Neural Networks With Fixed Value Khairul Azha A. Aziz Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka, Ayer Keroh, Melaka, Malaysia.

More information

COMPEL 17,1/2/3. This work was supported by the Greek General Secretariat of Research and Technology through the PENED 94 research project.

COMPEL 17,1/2/3. This work was supported by the Greek General Secretariat of Research and Technology through the PENED 94 research project. 382 Non-destructive testing of layered structures using generalised radial basis function networks trained by the orthogonal least squares learning algorithm I.T. Rekanos, T.V. Yioultsis and T.D. Tsiboukis

More information

INVESTIGATING DATA MINING BY ARTIFICIAL NEURAL NETWORK: A CASE OF REAL ESTATE PROPERTY EVALUATION

INVESTIGATING DATA MINING BY ARTIFICIAL NEURAL NETWORK: A CASE OF REAL ESTATE PROPERTY EVALUATION http:// INVESTIGATING DATA MINING BY ARTIFICIAL NEURAL NETWORK: A CASE OF REAL ESTATE PROPERTY EVALUATION 1 Rajat Pradhan, 2 Satish Kumar 1,2 Dept. of Electronics & Communication Engineering, A.S.E.T.,

More information

Visual Working Efficiency Analysis Method of Cockpit Based On ANN

Visual Working Efficiency Analysis Method of Cockpit Based On ANN Visual Working Efficiency Analysis Method of Cockpit Based On ANN Yingchun CHEN Commercial Aircraft Corporation of China,Ltd Dongdong WEI Fudan University Dept. of Mechanics an Science Engineering Gang

More information

Artificial Neural Network-Based Prediction of Human Posture

Artificial Neural Network-Based Prediction of Human Posture Artificial Neural Network-Based Prediction of Human Posture Abstract The use of an artificial neural network (ANN) in many practical complicated problems encourages its implementation in the digital human

More information

ISSN: ISO 9001:2008 Certified International Journal of Engineering and Innovative Technology (IJEIT) Volume 3, Issue 1, July 2013

ISSN: ISO 9001:2008 Certified International Journal of Engineering and Innovative Technology (IJEIT) Volume 3, Issue 1, July 2013 Application of Neural Network for Different Learning Parameter in Classification of Local Feature Image Annie anak Joseph, Chong Yung Fook Universiti Malaysia Sarawak, Faculty of Engineering, 94300, Kota

More information

An Integer Recurrent Artificial Neural Network for Classifying Feature Vectors

An Integer Recurrent Artificial Neural Network for Classifying Feature Vectors An Integer Recurrent Artificial Neural Network for Classifying Feature Vectors Roelof K Brouwer PEng, PhD University College of the Cariboo, Canada Abstract: The main contribution of this report is the

More information

Lecture 20: Neural Networks for NLP. Zubin Pahuja

Lecture 20: Neural Networks for NLP. Zubin Pahuja Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple

More information

Robustness of Selective Desensitization Perceptron Against Irrelevant and Partially Relevant Features in Pattern Classification

Robustness of Selective Desensitization Perceptron Against Irrelevant and Partially Relevant Features in Pattern Classification Robustness of Selective Desensitization Perceptron Against Irrelevant and Partially Relevant Features in Pattern Classification Tomohiro Tanno, Kazumasa Horie, Jun Izawa, and Masahiko Morita University

More information

The Prediction of Real estate Price Index based on Improved Neural Network Algorithm

The Prediction of Real estate Price Index based on Improved Neural Network Algorithm , pp.0-5 http://dx.doi.org/0.457/astl.05.8.03 The Prediction of Real estate Price Index based on Improved Neural Netor Algorithm Huan Ma, Ming Chen and Jianei Zhang Softare Engineering College, Zhengzhou

More information

Function approximation using RBF network. 10 basis functions and 25 data points.

Function approximation using RBF network. 10 basis functions and 25 data points. 1 Function approximation using RBF network F (x j ) = m 1 w i ϕ( x j t i ) i=1 j = 1... N, m 1 = 10, N = 25 10 basis functions and 25 data points. Basis function centers are plotted with circles and data

More information

Neural Networks. Prof. Dr. Rudolf Kruse. Computational Intelligence Group Faculty for Computer Science

Neural Networks. Prof. Dr. Rudolf Kruse. Computational Intelligence Group Faculty for Computer Science Neural Networks Prof. Dr. Rudolf Kruse Computational Intelligence Group Faculty for Computer Science kruse@iws.cs.uni-magdeburg.de Rudolf Kruse Neural Networks Radial Basis Function Networks Rudolf Kruse

More information

An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting.

An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. Mohammad Mahmudul Alam Mia, Shovasis Kumar Biswas, Monalisa Chowdhury Urmi, Abubakar

More information

International Research Journal of Computer Science (IRJCS) ISSN: Issue 09, Volume 4 (September 2017)

International Research Journal of Computer Science (IRJCS) ISSN: Issue 09, Volume 4 (September 2017) APPLICATION OF LRN AND BPNN USING TEMPORAL BACKPROPAGATION LEARNING FOR PREDICTION OF DISPLACEMENT Talvinder Singh, Munish Kumar C-DAC, Noida, India talvinder.grewaal@gmail.com,munishkumar@cdac.in Manuscript

More information

A Comparative Study of SVM Kernel Functions Based on Polynomial Coefficients and V-Transform Coefficients

A Comparative Study of SVM Kernel Functions Based on Polynomial Coefficients and V-Transform Coefficients www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 6 Issue 3 March 2017, Page No. 20765-20769 Index Copernicus value (2015): 58.10 DOI: 18535/ijecs/v6i3.65 A Comparative

More information

Performance Evaluation of a Radial Basis Function Neural Network Learning Algorithm for Function Approximation.

Performance Evaluation of a Radial Basis Function Neural Network Learning Algorithm for Function Approximation. Performance Evaluation of a Radial Basis Function Neural Network Learning Algorithm for Function Approximation. A.A. Khurshid PCEA, Nagpur, India A.P.Gokhale VNIT, Nagpur, India Abstract: This paper presents

More information

A neural network that classifies glass either as window or non-window depending on the glass chemistry.

A neural network that classifies glass either as window or non-window depending on the glass chemistry. A neural network that classifies glass either as window or non-window depending on the glass chemistry. Djaber Maouche Department of Electrical Electronic Engineering Cukurova University Adana, Turkey

More information

Chap.12 Kernel methods [Book, Chap.7]

Chap.12 Kernel methods [Book, Chap.7] Chap.12 Kernel methods [Book, Chap.7] Neural network methods became popular in the mid to late 1980s, but by the mid to late 1990s, kernel methods have also become popular in machine learning. The first

More information

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation K. Roy, U. Pal and B. B. Chaudhuri CVPR Unit; Indian Statistical Institute, Kolkata-108; India umapada@isical.ac.in

More information

IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL NETWORK (ANN) FOR FULL ADDER. Research Scholar, IIT Kharagpur.

IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL NETWORK (ANN) FOR FULL ADDER. Research Scholar, IIT Kharagpur. Journal of Analysis and Computation (JAC) (An International Peer Reviewed Journal), www.ijaconline.com, ISSN 0973-2861 Volume XI, Issue I, Jan- December 2018 IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL

More information

CHAPTER 6 COUNTER PROPAGATION NEURAL NETWORK IN GAIT RECOGNITION

CHAPTER 6 COUNTER PROPAGATION NEURAL NETWORK IN GAIT RECOGNITION 75 CHAPTER 6 COUNTER PROPAGATION NEURAL NETWORK IN GAIT RECOGNITION 6.1 INTRODUCTION Counter propagation network (CPN) was developed by Robert Hecht-Nielsen as a means to combine an unsupervised Kohonen

More information

Automatic basis selection for RBF networks using Stein s unbiased risk estimator

Automatic basis selection for RBF networks using Stein s unbiased risk estimator Automatic basis selection for RBF networks using Stein s unbiased risk estimator Ali Ghodsi School of omputer Science University of Waterloo University Avenue West NL G anada Email: aghodsib@cs.uwaterloo.ca

More information

Designing Radial Basis Neural Networks using a Distributed Architecture

Designing Radial Basis Neural Networks using a Distributed Architecture Designing Radial Basis Neural Networks using a Distributed Architecture J.M. Valls, A. Leal, I.M. Galván and J.M. Molina Computer Science Department Carlos III University of Madrid Avenida de la Universidad,

More information

An Edge Detection Method Using Back Propagation Neural Network

An Edge Detection Method Using Back Propagation Neural Network RESEARCH ARTICLE OPEN ACCESS An Edge Detection Method Using Bac Propagation Neural Netor Ms. Utarsha Kale*, Dr. S. M. Deoar** *Department of Electronics and Telecommunication, Sinhgad Institute of Technology

More information

Supervised Learning in Neural Networks (Part 2)

Supervised Learning in Neural Networks (Part 2) Supervised Learning in Neural Networks (Part 2) Multilayer neural networks (back-propagation training algorithm) The input signals are propagated in a forward direction on a layer-bylayer basis. Learning

More information

NNIGnets, Neural Networks Software

NNIGnets, Neural Networks Software NNIGnets, Neural Networks Software Tânia Fontes 1, Vânia Lopes 1, Luís M. Silva 1, Jorge M. Santos 1,2, and Joaquim Marques de Sá 1 1 INEB - Instituto de Engenharia Biomédica, Campus FEUP (Faculdade de

More information

Neural Network Neurons

Neural Network Neurons Neural Networks Neural Network Neurons 1 Receives n inputs (plus a bias term) Multiplies each input by its weight Applies activation function to the sum of results Outputs result Activation Functions Given

More information

Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine

Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine M. Vijay Kumar Reddy 1 1 Department of Mechanical Engineering, Annamacharya Institute of Technology and Sciences,

More information

KINEMATIC ANALYSIS OF ADEPT VIPER USING NEURAL NETWORK

KINEMATIC ANALYSIS OF ADEPT VIPER USING NEURAL NETWORK Proceedings of the National Conference on Trends and Advances in Mechanical Engineering, YMCA Institute of Engineering, Faridabad, Haryana., Dec 9-10, 2006. KINEMATIC ANALYSIS OF ADEPT VIPER USING NEURAL

More information

Locally Weighted Learning for Control. Alexander Skoglund Machine Learning Course AASS, June 2005

Locally Weighted Learning for Control. Alexander Skoglund Machine Learning Course AASS, June 2005 Locally Weighted Learning for Control Alexander Skoglund Machine Learning Course AASS, June 2005 Outline Locally Weighted Learning, Christopher G. Atkeson et. al. in Artificial Intelligence Review, 11:11-73,1997

More information

SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training

SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training John Sum and Kevin Ho Institute of Technology Management, National Chung Hsing University Taichung 4, Taiwan. pfsum@nchu.edu.tw

More information

CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN)

CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN) 128 CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN) Various mathematical techniques like regression analysis and software tools have helped to develop a model using equation, which

More information

Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value

Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value IJCSES International Journal of Computer Sciences and Engineering Systems, Vol., No. 3, July 2011 CSES International 2011 ISSN 0973-06 Face Detection Using Radial Basis Function Neural Networks with Fixed

More information

Liquefaction Analysis in 3D based on Neural Network Algorithm

Liquefaction Analysis in 3D based on Neural Network Algorithm Liquefaction Analysis in 3D based on Neural Network Algorithm M. Tolon Istanbul Technical University, Turkey D. Ural Istanbul Technical University, Turkey SUMMARY: Simplified techniques based on in situ

More information

Nelder-Mead Enhanced Extreme Learning Machine

Nelder-Mead Enhanced Extreme Learning Machine Philip Reiner, Bogdan M. Wilamowski, "Nelder-Mead Enhanced Extreme Learning Machine", 7-th IEEE Intelligent Engineering Systems Conference, INES 23, Costa Rica, June 9-2., 29, pp. 225-23 Nelder-Mead Enhanced

More information

THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM

THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM M. Sivakumar 1 and R. M. S. Parvathi 2 1 Anna University, Tamilnadu, India 2 Sengunthar College of Engineering, Tamilnadu,

More information

Gauss-Sigmoid Neural Network

Gauss-Sigmoid Neural Network Gauss-Sigmoid Neural Network Katsunari SHIBATA and Koji ITO Tokyo Institute of Technology, Yokohama, JAPAN shibata@ito.dis.titech.ac.jp Abstract- Recently RBF(Radial Basis Function)-based networks have

More information

Multi Layer Perceptron with Back Propagation. User Manual

Multi Layer Perceptron with Back Propagation. User Manual Multi Layer Perceptron with Back Propagation User Manual DAME-MAN-NA-0011 Issue: 1.3 Date: September 03, 2013 Author: S. Cavuoti, M. Brescia Doc. : MLPBP_UserManual_DAME-MAN-NA-0011-Rel1.3 1 INDEX 1 Introduction...

More information

International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS)

International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS) International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) International Journal of Emerging Technologies in Computational

More information

Data Mining. Neural Networks

Data Mining. Neural Networks Data Mining Neural Networks Goals for this Unit Basic understanding of Neural Networks and how they work Ability to use Neural Networks to solve real problems Understand when neural networks may be most

More information

Design and Performance Analysis of and Gate using Synaptic Inputs for Neural Network Application

Design and Performance Analysis of and Gate using Synaptic Inputs for Neural Network Application IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 12 May 2015 ISSN (online): 2349-6010 Design and Performance Analysis of and Gate using Synaptic Inputs for Neural

More information

742 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 13, NO. 6, DECEMBER Dong Zhang, Luo-Feng Deng, Kai-Yuan Cai, and Albert So

742 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 13, NO. 6, DECEMBER Dong Zhang, Luo-Feng Deng, Kai-Yuan Cai, and Albert So 742 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL 13, NO 6, DECEMBER 2005 Fuzzy Nonlinear Regression With Fuzzified Radial Basis Function Network Dong Zhang, Luo-Feng Deng, Kai-Yuan Cai, and Albert So Abstract

More information

Neuron Selectivity as a Biologically Plausible Alternative to Backpropagation

Neuron Selectivity as a Biologically Plausible Alternative to Backpropagation Neuron Selectivity as a Biologically Plausible Alternative to Backpropagation C.J. Norsigian Department of Bioengineering cnorsigi@eng.ucsd.edu Vishwajith Ramesh Department of Bioengineering vramesh@eng.ucsd.edu

More information

MATLAB representation of neural network Outline Neural network with single-layer of neurons. Neural network with multiple-layer of neurons.

MATLAB representation of neural network Outline Neural network with single-layer of neurons. Neural network with multiple-layer of neurons. MATLAB representation of neural network Outline Neural network with single-layer of neurons. Neural network with multiple-layer of neurons. Introduction: Neural Network topologies (Typical Architectures)

More information

Radial Basis Function Networks: Algorithms

Radial Basis Function Networks: Algorithms Radial Basis Function Networks: Algorithms Neural Computation : Lecture 14 John A. Bullinaria, 2015 1. The RBF Mapping 2. The RBF Network Architecture 3. Computational Power of RBF Networks 4. Training

More information

In the Name of God. Lecture 17: ANFIS Adaptive Network-Based Fuzzy Inference System

In the Name of God. Lecture 17: ANFIS Adaptive Network-Based Fuzzy Inference System In the Name of God Lecture 17: ANFIS Adaptive Network-Based Fuzzy Inference System Outline ANFIS Architecture Hybrid Learning Algorithm Learning Methods that Cross-Fertilize ANFIS and RBFN ANFIS as a universal

More information

Introduction to Neural Networks: Structure and Training

Introduction to Neural Networks: Structure and Training Introduction to Neural Networks: Structure and Training Qi-Jun Zhang Department of Electronics Carleton University, Ottawa, ON, Canada A Quick Illustration Example: Neural Network Model for Delay Estimation

More information

Multilayer Feed-forward networks

Multilayer Feed-forward networks Multi Feed-forward networks 1. Computational models of McCulloch and Pitts proposed a binary threshold unit as a computational model for artificial neuron. This first type of neuron has been generalized

More information

6. NEURAL NETWORK BASED PATH PLANNING ALGORITHM 6.1 INTRODUCTION

6. NEURAL NETWORK BASED PATH PLANNING ALGORITHM 6.1 INTRODUCTION 6 NEURAL NETWORK BASED PATH PLANNING ALGORITHM 61 INTRODUCTION In previous chapters path planning algorithms such as trigonometry based path planning algorithm and direction based path planning algorithm

More information

THE NEURAL NETWORKS: APPLICATION AND OPTIMIZATION APPLICATION OF LEVENBERG-MARQUARDT ALGORITHM FOR TIFINAGH CHARACTER RECOGNITION

THE NEURAL NETWORKS: APPLICATION AND OPTIMIZATION APPLICATION OF LEVENBERG-MARQUARDT ALGORITHM FOR TIFINAGH CHARACTER RECOGNITION International Journal of Science, Environment and Technology, Vol. 2, No 5, 2013, 779 786 ISSN 2278-3687 (O) THE NEURAL NETWORKS: APPLICATION AND OPTIMIZATION APPLICATION OF LEVENBERG-MARQUARDT ALGORITHM

More information

Comparative Analysis of Unsupervised and Supervised Image Classification Techniques

Comparative Analysis of Unsupervised and Supervised Image Classification Techniques ational Conference on Recent Trends in Engineering & Technology Comparative Analysis of Unsupervised and Supervised Image Classification Techniques Sunayana G. Domadia Dr.Tanish Zaveri Assistant Professor

More information

Improving Generalization of Radial Basis Function Network with Adaptive Multi-Objective Particle Swarm Optimization

Improving Generalization of Radial Basis Function Network with Adaptive Multi-Objective Particle Swarm Optimization Proceedings of the 009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 009 Improving Generalization of Radial Basis Function Network with Adaptive Multi-Obective

More information

Implementation of a Library for Artificial Neural Networks in C

Implementation of a Library for Artificial Neural Networks in C Implementation of a Library for Artificial Neural Networks in C Jack Breese TJHSST Computer Systems Lab 2007-2008 June 10, 2008 1 Abstract In modern computing, there are several approaches to pattern recognition

More information

Climate Precipitation Prediction by Neural Network

Climate Precipitation Prediction by Neural Network Journal of Mathematics and System Science 5 (205) 207-23 doi: 0.7265/259-529/205.05.005 D DAVID PUBLISHING Juliana Aparecida Anochi, Haroldo Fraga de Campos Velho 2. Applied Computing Graduate Program,

More information

Keywords: ANN; network topology; bathymetric model; representability.

Keywords: ANN; network topology; bathymetric model; representability. Proceedings of ninth International Conference on Hydro-Science and Engineering (ICHE 2010), IIT Proceedings Madras, Chennai, of ICHE2010, India. IIT Madras, Aug 2-5,2010 DETERMINATION OF 2 NETWORK - 5

More information

ESTIMATION OF SUBSURFACE QANATS DEPTH BY MULTI LAYER PERCEPTRON NEURAL NETWORK VIA MICROGRAVITY DATA

ESTIMATION OF SUBSURFACE QANATS DEPTH BY MULTI LAYER PERCEPTRON NEURAL NETWORK VIA MICROGRAVITY DATA Advances in Geosciences Vol. 20: Solid Earth (2008) Ed. Kenji Satake c World Scientific Publishing Company ESTIMATION OF SUBSURFACE QANATS DEPTH BY MULTI LAYER PERCEPTRON NEURAL NETWORK VIA MICROGRAVITY

More information

Non-standard geometry scaling effects in SiGe HBTs

Non-standard geometry scaling effects in SiGe HBTs Non-standard geometry scaling effects in SiGe HBTs M. Schröter 1),2), S. Lehmann 1), D. Celi 3) 1) Chair for Electron Devices and Integr. Circuits, Univ. of Technol. Dresden, Germany 2) ECE Dept., University

More information

Week 3: Perceptron and Multi-layer Perceptron

Week 3: Perceptron and Multi-layer Perceptron Week 3: Perceptron and Multi-layer Perceptron Phong Le, Willem Zuidema November 12, 2013 Last week we studied two famous biological neuron models, Fitzhugh-Nagumo model and Izhikevich model. This week,

More information

Multi-Layer Perceptrons with B-SpIine Receptive Field Functions

Multi-Layer Perceptrons with B-SpIine Receptive Field Functions Multi-Layer Perceptrons with B-SpIine Receptive Field Functions Stephen H. Lane, Marshall G. Flax, David A. Handelman and JackJ. Gelfand Human Information Processing Group Department of Psychology Princeton

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

Neuro-Fuzzy Computing

Neuro-Fuzzy Computing CSE531 Neuro-Fuzzy Computing Tutorial/Assignment 2: Adaline and Multilayer Perceptron About this tutorial The objective of this tutorial is to study: You can create a single (composite) layer of neurons

More information

CS6220: DATA MINING TECHNIQUES

CS6220: DATA MINING TECHNIQUES CS6220: DATA MINING TECHNIQUES Image Data: Classification via Neural Networks Instructor: Yizhou Sun yzsun@ccs.neu.edu November 19, 2015 Methods to Learn Classification Clustering Frequent Pattern Mining

More information

A New RBF Neural Network With Boundary Value Constraints

A New RBF Neural Network With Boundary Value Constraints 98 IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS PART B: CYBERNETICS, VOL. 39, NO. 1, FEBRUARY 009 A New RBF Neural Network With Boundary Value Constraints Xia Hong, Senior Member, IEEE,and Sheng

More information

Intelligent Methods in Modelling and Simulation of Complex Systems

Intelligent Methods in Modelling and Simulation of Complex Systems SNE O V E R V I E W N OTE Intelligent Methods in Modelling and Simulation of Complex Systems Esko K. Juuso * Control Engineering Laboratory Department of Process and Environmental Engineering, P.O.Box

More information

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different

More information

IN recent years, neural networks have attracted considerable attention

IN recent years, neural networks have attracted considerable attention Multilayer Perceptron: Architecture Optimization and Training Hassan Ramchoun, Mohammed Amine Janati Idrissi, Youssef Ghanou, Mohamed Ettaouil Modeling and Scientific Computing Laboratory, Faculty of Science

More information

Simple Emitter and Collector Scaling Approach with VBIC for Low-cost SiGe:C HBT s

Simple Emitter and Collector Scaling Approach with VBIC for Low-cost SiGe:C HBT s Simple Emitter and Collector Scaling Approach with VBIC for Low-cost SiGe:C HBT s René F. Scholz *, B. Senapati*, A. Chakravorty #, D. Knoll *, C.K. Maiti # * IHP, Frankfurt (Oder), Germany # IIT, Kharagpur,

More information

CHAPTER VI BACK PROPAGATION ALGORITHM

CHAPTER VI BACK PROPAGATION ALGORITHM 6.1 Introduction CHAPTER VI BACK PROPAGATION ALGORITHM In the previous chapter, we analysed that multiple layer perceptrons are effectively applied to handle tricky problems if trained with a vastly accepted

More information

ESSENTIALLY, system modeling is the task of building

ESSENTIALLY, system modeling is the task of building IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 53, NO. 4, AUGUST 2006 1269 An Algorithm for Extracting Fuzzy Rules Based on RBF Neural Network Wen Li and Yoichi Hori, Fellow, IEEE Abstract A four-layer

More information

CS 6501: Deep Learning for Computer Graphics. Training Neural Networks II. Connelly Barnes

CS 6501: Deep Learning for Computer Graphics. Training Neural Networks II. Connelly Barnes CS 6501: Deep Learning for Computer Graphics Training Neural Networks II Connelly Barnes Overview Preprocessing Initialization Vanishing/exploding gradients problem Batch normalization Dropout Additional

More information

II. ARTIFICIAL NEURAL NETWORK

II. ARTIFICIAL NEURAL NETWORK Applications of Artificial Neural Networks in Power Systems: A Review Harsh Sareen 1, Palak Grover 2 1, 2 HMR Institute of Technology and Management Hamidpur New Delhi, India Abstract: A standout amongst

More information

A Hybrid Location Algorithm Based on BP Neural Networks for Mobile Position Estimation

A Hybrid Location Algorithm Based on BP Neural Networks for Mobile Position Estimation 162 IJCSNS International Journal of Computer Science and Network Security, VOL.6 No.7A, July 2006 A Hybrid Location Algorithm Based on BP Neural Networks for Mobile Position Estimation Zhao Ping 1, Li

More information

Computer-aided detection of clustered microcalcifications in digital mammograms.

Computer-aided detection of clustered microcalcifications in digital mammograms. Computer-aided detection of clustered microcalcifications in digital mammograms. Stelios Halkiotis, John Mantas & Taxiarchis Botsis. University of Athens Faculty of Nursing- Health Informatics Laboratory.

More information