Search results for: Fast Neural Networks
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3087

Search results for: Fast Neural Networks

3087 A Fast Neural Algorithm for Serial Code Detection in a Stream of Sequential Data

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In recent years, fast neural networks for object/face detection have been introduced based on cross correlation in the frequency domain between the input matrix and the hidden weights of neural networks. In our previous papers [3,4], fast neural networks for certain code detection was introduced. It was proved in [10] that for fast neural networks to give the same correct results as conventional neural networks, both the weights of neural networks and the input matrix must be symmetric. This condition made those fast neural networks slower than conventional neural networks. Another symmetric form for the input matrix was introduced in [1-9] to speed up the operation of these fast neural networks. Here, corrections for the cross correlation equations (given in [13,15,16]) to compensate for the symmetry condition are presented. After these corrections, it is proved mathematically that the number of computation steps required for fast neural networks is less than that needed by classical neural networks. Furthermore, there is no need for converting the input data into symmetric form. Moreover, such new idea is applied to increase the speed of neural networks in case of processing complex values. Simulation results after these corrections using MATLAB confirm the theoretical computations.

Keywords: Fast Code/Data Detection, Neural Networks, Cross Correlation, real/complex values.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1569
3086 Sub-Image Detection Using Fast Neural Processors and Image Decomposition

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.

Keywords: Fast Neural Networks, 2D-FFT, CrossCorrelation, Image decomposition, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2118
3085 Fast Object/Face Detection Using Neural Networks and Fast Fourier Transform

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, fast neural networks for object/face detection were presented in [1-3]. The speed up factor of these networks relies on performing cross correlation in the frequency domain between the input image and the weights of the hidden layer. But, these equations given in [1-3] for conventional and fast neural networks are not valid for many reasons presented here. In this paper, correct equations for cross correlation in the spatial and frequency domains are presented. Furthermore, correct formulas for the number of computation steps required by conventional and fast neural networks given in [1-3] are introduced. A new formula for the speed up ratio is established. Also, corrections for the equations of fast multi scale object/face detection are given. Moreover, commutative cross correlation is achieved. Simulation results show that sub-image detection based on cross correlation in the frequency domain is faster than classical neural networks.

Keywords: Conventional Neural Networks, Fast Neural Networks, Cross Correlation in the Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2388
3084 Fast Complex Valued Time Delay Neural Networks

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Here, a new idea to speed up the operation of complex valued time delay neural networks is presented. The whole data are collected together in a long vector and then tested as a one input pattern. The proposed fast complex valued time delay neural networks uses cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically that the number of computation steps required for the presented fast complex valued time delay neural networks is less than that needed by classical time delay neural networks. Simulation results using MATLAB confirm the theoretical computations.

Keywords: Fast Complex Valued Time Delay Neural Networks, Cross Correlation, Frequency Domain

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1771
3083 A Modified Cross Correlation in the Frequency Domain for Fast Pattern Detection Using Neural Networks

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, neural networks have shown good results for detection of a certain pattern in a given image. In our previous papers [1-5], a fast algorithm for pattern detection using neural networks was presented. Such algorithm was designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. Image conversion into symmetric shape was established so that fast neural networks can give the same results as conventional neural networks. Another configuration of symmetry was suggested in [3,4] to improve the speed up ratio. In this paper, our previous algorithm for fast neural networks is developed. The frequency domain cross correlation is modified in order to compensate for the symmetric condition which is required by the input image. Two new ideas are introduced to modify the cross correlation algorithm. Both methods accelerate the speed of the fast neural networks as there is no need for converting the input image into symmetric one as previous. Theoretical and practical results show that both approaches provide faster speed up ratio than the previous algorithm.

Keywords: Fast Pattern Detection, Neural Networks, Modified Cross Correlation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1683
3082 Fast Forecasting of Stock Market Prices by using New High Speed Time Delay Neural Networks

Authors: Hazem M. El-Bakry, Nikos Mastorakis

Abstract:

Fast forecasting of stock market prices is very important for strategic planning. In this paper, a new approach for fast forecasting of stock market prices is presented. Such algorithm uses new high speed time delay neural networks (HSTDNNs). The operation of these networks relies on performing cross correlation in the frequency domain between the input data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the presented HSTDNNs is less than that needed by traditional time delay neural networks (TTDNNs). Simulation results using MATLAB confirm the theoretical computations.

Keywords: Fast Forecasting, Stock Market Prices, Time Delay NeuralNetworks, Cross Correlation, Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2007
3081 A Combined Neural Network Approach to Soccer Player Prediction

Authors: Wenbin Zhang, Hantian Wu, Jian Tang

Abstract:

An artificial neural network is a mathematical model inspired by biological neural networks. There are several kinds of neural networks and they are widely used in many areas, such as: prediction, detection, and classification. Meanwhile, in day to day life, people always have to make many difficult decisions. For example, the coach of a soccer club has to decide which offensive player to be selected to play in a certain game. This work describes a novel Neural Network using a combination of the General Regression Neural Network and the Probabilistic Neural Networks to help a soccer coach make an informed decision.

Keywords: General Regression Neural Network, Probabilistic Neural Networks, Neural function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3702
3080 Improving Quality of Business Networks for Information Systems

Authors: Hazem M. El-Bakry, Ahmed Atwan

Abstract:

Computer networks are essential part in computerbased information systems. The performance of these networks has a great influence on the whole information system. Measuring the usability criteria and customers satisfaction on small computer network is very important. In this article, an effective approach for measuring the usability of business network in an information system is introduced. The usability process for networking provides us with a flexible and a cost-effective way to assess the usability of a network and its products. In addition, the proposed approach can be used to certify network product usability late in the development cycle. Furthermore, it can be used to help in developing usable interfaces very early in the cycle and to give a way to measure, track, and improve usability. Moreover, a new approach for fast information processing over computer networks is presented. The entire data are collected together in a long vector and then tested as a one input pattern. Proposed fast time delay neural networks (FTDNNs) use cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the presented time delay neural networks is less than that needed by conventional time delay neural networks (CTDNNs). Simulation results using MATLAB confirm the theoretical computations.

Keywords: Usability Criteria, Computer Networks, Fast Information Processing, Cross Correlation, Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1954
3079 The Multi-Layered Perceptrons Neural Networks for the Prediction of Daily Solar Radiation

Authors: Radouane Iqdour, Abdelouhab Zeroual

Abstract:

The Multi-Layered Perceptron (MLP) Neural networks have been very successful in a number of signal processing applications. In this work we have studied the possibilities and the met difficulties in the application of the MLP neural networks for the prediction of daily solar radiation data. We have used the Polack-Ribière algorithm for training the neural networks. A comparison, in term of the statistical indicators, with a linear model most used in literature, is also performed, and the obtained results show that the neural networks are more efficient and gave the best results.

Keywords: Daily solar radiation, Prediction, MLP neural networks, linear model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1272
3078 A Model-following Adaptive Controller for Linear/Nonlinear Plantsusing Radial Basis Function Neural Networks

Authors: Yuichi Masukake, Yoshihisa Ishida

Abstract:

In this paper, we proposed a method to design a model-following adaptive controller for linear/nonlinear plants. Radial basis function neural networks (RBF-NNs), which are known for their stable learning capability and fast training, are used to identify linear/nonlinear plants. Simulation results show that the proposed method is effective in controlling both linear and nonlinear plants with disturbance in the plant input.

Keywords: Linear/nonlinear plants, neural networks, radial basisfunction networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1423
3077 Integrating Fast Karnough Map and Modular Neural Networks for Simplification and Realization of Complex Boolean Functions

Authors: Hazem M. El-Bakry

Abstract:

In this paper a new fast simplification method is presented. Such method realizes Karnough map with large number of variables. In order to accelerate the operation of the proposed method, a new approach for fast detection of group of ones is presented. Such approach implemented in the frequency domain. The search operation relies on performing cross correlation in the frequency domain rather than time one. It is proved mathematically and practically that the number of computation steps required for the presented method is less than that needed by conventional cross correlation. Simulation results using MATLAB confirm the theoretical computations. Furthermore, a powerful solution for realization of complex functions is given. The simplified functions are implemented by using a new desigen for neural networks. Neural networks are used because they are fault tolerance and as a result they can recognize signals even with noise or distortion. This is very useful for logic functions used in data and computer communications. Moreover, the implemented functions are realized with minimum amount of components. This is done by using modular neural nets (MNNs) that divide the input space into several homogenous regions. Such approach is applied to implement XOR function, 16 logic functions on one bit level, and 2-bit digital multiplier. Compared to previous non- modular designs, a clear reduction in the order of computations and hardware requirements is achieved.

Keywords: Boolean functions, simplification, Karnough map, implementation of logic functions, modular neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2017
3076 Application of Wavelet Neural Networks in Optimization of Skeletal Buildings under Frequency Constraints

Authors: Mohammad Reza Ghasemi, Amin Ghorbani

Abstract:

The main goal of the present work is to decrease the computational burden for optimum design of steel frames with frequency constraints using a new type of neural networks called Wavelet Neural Network. It is contested to train a suitable neural network for frequency approximation work as the analysis program. The combination of wavelet theory and Neural Networks (NN) has lead to the development of wavelet neural networks. Wavelet neural networks are feed-forward networks using wavelet as activation function. Wavelets are mathematical functions within suitable inner parameters, which help them to approximate arbitrary functions. WNN was used to predict the frequency of the structures. In WNN a RAtional function with Second order Poles (RASP) wavelet was used as a transfer function. It is shown that the convergence speed was faster than other neural networks. Also comparisons of WNN with the embedded Artificial Neural Network (ANN) and with approximate techniques and also with analytical solutions are available in the literature.

Keywords: Weight Minimization, Frequency Constraints, Steel Frames, ANN, WNN, RASP Function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1678
3075 Diagnosis of Ovarian Cancer with Proteomic Patterns in Serum using Independent Component Analysis and Neural Networks

Authors: Simone C. F. Neves, Lúcio F. A. Campos, Ewaldo Santana, Ginalber L. O. Serra, Allan K. Barros

Abstract:

We propose a method for discrimination and classification of ovarian with benign, malignant and normal tissue using independent component analysis and neural networks. The method was tested for a proteomic patters set from A database, and radial basis functions neural networks. The best performance was obtained with probabilistic neural networks, resulting I 99% success rate, with 98% of specificity e 100% of sensitivity.

Keywords: Cancer ovarian, Proteomic patterns in serum, independent component analysis and neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1776
3074 A New High Speed Neural Model for Fast Character Recognition Using Cross Correlation and Matrix Decomposition

Authors: Hazem M. El-Bakry

Abstract:

Neural processors have shown good results for detecting a certain character in a given input matrix. In this paper, a new idead to speed up the operation of neural processors for character detection is presented. Such processors are designed based on cross correlation in the frequency domain between the input matrix and the weights of neural networks. This approach is developed to reduce the computation steps required by these faster neural networks for the searching process. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single faster neural processor. Furthermore, faster character detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of faster neural networks. In contrast to using only faster neural processors, the speed up ratio is increased with the size of the input image when using faster neural processors and image decomposition. Moreover, the problem of local subimage normalization in the frequency domain is solved. The effect of image normalization on the speed up ratio of character detection is discussed. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. The overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

Keywords: Fast Character Detection, Neural Processors, Cross Correlation, Image Normalization, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1481
3073 Optimal Document Archiving and Fast Information Retrieval

Authors: Hazem M. El-Bakry, Ahmed A. Mohammed

Abstract:

In this paper, an intelligent algorithm for optimal document archiving is presented. It is kown that electronic archives are very important for information system management. Minimizing the size of the stored data in electronic archive is a main issue to reduce the physical storage area. Here, the effect of different types of Arabic fonts on electronic archives size is discussed. Simulation results show that PDF is the best file format for storage of the Arabic documents in electronic archive. Furthermore, fast information detection in a given PDF file is introduced. Such approach uses fast neural networks (FNNs) implemented in the frequency domain. The operation of these networks relies on performing cross correlation in the frequency domain rather than spatial one. It is proved mathematically and practically that the number of computation steps required for the presented FNNs is less than that needed by conventional neural networks (CNNs). Simulation results using MATLAB confirm the theoretical computations.

Keywords: Information Storage and Retrieval, Electronic Archiving, Fast Information Detection, Cross Correlation, Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1519
3072 Analysis of Periodic Solution of Delay Fuzzy BAM Neural Networks

Authors: Qianhong Zhang, Lihui Yang, Daixi Liao

Abstract:

In this paper, by employing a new Lyapunov functional and an elementary inequality analysis technique, some sufficient conditions are derived to ensure the existence and uniqueness of periodic oscillatory solution for fuzzy bi-directional memory (BAM) neural networks with time-varying delays, and all other solutions of the fuzzy BAM neural networks converge the uniqueness periodic solution. These criteria are presented in terms of system parameters and have important leading significance in the design and applications of neural networks. Moreover an example is given to illustrate the effectiveness and feasible of results obtained.

Keywords: Fuzzy BAM neural networks, Periodic solution, Global exponential stability, Time-varying delays

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1447
3071 Avoiding Catastrophic Forgetting by a Dual-Network Memory Model Using a Chaotic Neural Network

Authors: Motonobu Hattori

Abstract:

In neural networks, when new patterns are learned by a network, the new information radically interferes with previously stored patterns. This drawback is called catastrophic forgetting or catastrophic interference. In this paper, we propose a biologically inspired neural network model which overcomes this problem. The proposed model consists of two distinct networks: one is a Hopfield type of chaotic associative memory and the other is a multilayer neural network. We consider that these networks correspond to the hippocampus and the neocortex of the brain, respectively. Information given is firstly stored in the hippocampal network with fast learning algorithm. Then the stored information is recalled by chaotic behavior of each neuron in the hippocampal network. Finally, it is consolidated in the neocortical network by using pseudopatterns. Computer simulation results show that the proposed model has much better ability to avoid catastrophic forgetting in comparison with conventional models.

Keywords: catastrophic forgetting, chaotic neural network, complementary learning systems, dual-network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2034
3070 Integrating Fast Karnough Map and Modular Neural Networks for Simplification and Realization of Complex Boolean Functions

Authors: Hazem M. El-Bakry

Abstract:

In this paper a new fast simplification method is presented. Such method realizes Karnough map with large number of variables. In order to accelerate the operation of the proposed method, a new approach for fast detection of group of ones is presented. Such approach implemented in the frequency domain. The search operation relies on performing cross correlation in the frequency domain rather than time one. It is proved mathematically and practically that the number of computation steps required for the presented method is less than that needed by conventional cross correlation. Simulation results using MATLAB confirm the theoretical computations. Furthermore, a powerful solution for realization of complex functions is given. The simplified functions are implemented by using a new desigen for neural networks. Neural networks are used because they are fault tolerance and as a result they can recognize signals even with noise or distortion. This is very useful for logic functions used in data and computer communications. Moreover, the implemented functions are realized with minimum amount of components. This is done by using modular neural nets (MNNs) that divide the input space into several homogenous regions. Such approach is applied to implement XOR function, 16 logic functions on one bit level, and 2-bit digital multiplier. Compared to previous non- modular designs, a clear reduction in the order of computations and hardware requirements is achieved.

Keywords: Boolean Functions, Simplification, KarnoughMap, Implementation of Logic Functions, Modular NeuralNetworks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1759
3069 Neural Network Ensemble-based Solar Power Generation Short-Term Forecasting

Authors: A. Chaouachi, R.M. Kamel, R. Ichikawa, H. Hayashi, K. Nagasaka

Abstract:

This paper presents the applicability of artificial neural networks for 24 hour ahead solar power generation forecasting of a 20 kW photovoltaic system, the developed forecasting is suitable for a reliable Microgrid energy management. In total four neural networks were proposed, namely: multi-layred perceptron, radial basis function, recurrent and a neural network ensemble consisting in ensemble of bagged networks. Forecasting reliability of the proposed neural networks was carried out in terms forecasting error performance basing on statistical and graphical methods. The experimental results showed that all the proposed networks achieved an acceptable forecasting accuracy. In term of comparison the neural network ensemble gives the highest precision forecasting comparing to the conventional networks. In fact, each network of the ensemble over-fits to some extent and leads to a diversity which enhances the noise tolerance and the forecasting generalization performance comparing to the conventional networks.

Keywords: Neural network ensemble, Solar power generation, 24 hour forecasting, Comparative study

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3216
3068 The Impact of the Number of Neurons in the Hidden Layer on the Performance of MLP Neural Network: Application to the Fast Identification of Toxic Gases

Authors: Slimane Ouhmad, Abdellah Halimi

Abstract:

In this work, neural networks methods MLP type were applied to a database from an array of six sensors for the detection of three toxic gases. The choice of the number of hidden layers and the weight values are influential on the convergence of the learning algorithm. We proposed, in this article, a mathematical formula to determine the optimal number of hidden layers and good weight values based on the method of back propagation of errors. The results of this modeling have improved discrimination of these gases and optimized the computation time. The model presented here has proven to be an effective application for the fast identification of toxic gases.

Keywords: Back-propagation, Computing time, Fast identification, MLP neural network, Number of neurons in the hidden layer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2205
3067 Function Approximation with Radial Basis Function Neural Networks via FIR Filter

Authors: Kyu Chul Lee, Sung Hyun Yoo, Choon Ki Ahn, Myo Taeg Lim

Abstract:

Recent experimental evidences have shown that because of a fast convergence and a nice accuracy, neural networks training via extended kalman filter (EKF) method is widely applied. However, as to an uncertainty of the system dynamics or modeling error, the performance of the method is unreliable. In order to overcome this problem in this paper, a new finite impulse response (FIR) filter based learning algorithm is proposed to train radial basis function neural networks (RBFN) for nonlinear function approximation. Compared to the EKF training method, the proposed FIR filter training method is more robust to those environmental conditions. Furthermore , the number of centers will be considered since it affects the performance of approximation.

Keywords: Extended kalmin filter (EKF), classification problem, radial basis function networks (RBFN), finite impulse response (FIR)filter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2347
3066 Application New Approach with Two Networks Slow and Fast on the Asynchronous Machine

Authors: Samia Salah, M’hamed Hadj Sadok, Abderrezak Guessoum

Abstract:

In this paper, we propose a new modular approach called neuroglial consisting of two neural networks slow and fast which emulates a biological reality recently discovered. The implementation is based on complex multi-time scale systems; validation is performed on the model of the asynchronous machine. We applied the geometric approach based on the Gerschgorin circles for the decoupling of fast and slow variables, and the method of singular perturbations for the development of reductions models.

This new architecture allows for smaller networks with less complexity and better performance in terms of mean square error and convergence than the single network model.

Keywords: Gerschgorin’s Circles, Neuroglial Network, Multi time scales systems, Singular perturbation method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1547
3065 Investigation of Some Technical Indexes inStock Forecasting Using Neural Networks

Authors: Myungsook Klassen

Abstract:

Training neural networks to capture an intrinsic property of a large volume of high dimensional data is a difficult task, as the training process is computationally expensive. Input attributes should be carefully selected to keep the dimensionality of input vectors relatively small. Technical indexes commonly used for stock market prediction using neural networks are investigated to determine its effectiveness as inputs. The feed forward neural network of Levenberg-Marquardt algorithm is applied to perform one step ahead forecasting of NASDAQ and Dow stock prices.

Keywords: Stock Market Prediction, Neural Networks, Levenberg-Marquadt Algorithm, Technical Indexes

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1890
3064 Fast Adjustable Threshold for Uniform Neural Network Quantization

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: Distillation, machine learning, neural networks, quantization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 673
3063 Using Artificial Neural Networks for Optical Imaging of Fluorescent Biomarkers

Authors: K. A. Laptinskiy, S. A. Burikov, A. M. Vervald, S. A. Dolenko, T. A. Dolenko

Abstract:

The article presents the results of the application of artificial neural networks to separate the fluorescent contribution of nanodiamonds used as biomarkers, adsorbents and carriers of drugs in biomedicine, from a fluorescent background of own biological fluorophores. The principal possibility of solving this problem is shown. Use of neural network architecture let to detect fluorescence of nanodiamonds against the background autofluorescence of egg white with high accuracy - better than 3 ug/ml.

Keywords: Artificial neural networks, fluorescence, data aggregation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2046
3062 Novel Approach for Promoting the Generalization Ability of Neural Networks

Authors: Naiqin Feng, Fang Wang, Yuhui Qiu

Abstract:

A new approach to promote the generalization ability of neural networks is presented. It is based on the point of view of fuzzy theory. This approach is implemented through shrinking or magnifying the input vector, thereby reducing the difference between training set and testing set. It is called “shrinking-magnifying approach" (SMA). At the same time, a new algorithm; α-algorithm is presented to find out the appropriate shrinking-magnifying-factor (SMF) α and obtain better generalization ability of neural networks. Quite a few simulation experiments serve to study the effect of SMA and α-algorithm. The experiment results are discussed in detail, and the function principle of SMA is analyzed in theory. The results of experiments and analyses show that the new approach is not only simpler and easier, but also is very effective to many neural networks and many classification problems. In our experiments, the proportions promoting the generalization ability of neural networks have even reached 90%.

Keywords: Fuzzy theory, generalization, misclassification rate, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1481
3061 Accelerating Integer Neural Networks On Low Cost DSPs

Authors: Thomas Behan, Zaiyi Liao, Lian Zhao, Chunting Yang

Abstract:

In this paper, low end Digital Signal Processors (DSPs) are applied to accelerate integer neural networks. The use of DSPs to accelerate neural networks has been a topic of study for some time, and has demonstrated significant performance improvements. Recently, work has been done on integer only neural networks, which greatly reduces hardware requirements, and thus allows for cheaper hardware implementation. DSPs with Arithmetic Logic Units (ALUs) that support floating or fixed point arithmetic are generally more expensive than their integer only counterparts due to increased circuit complexity. However if the need for floating or fixed point math operation can be removed, then simpler, lower cost DSPs can be used. To achieve this, an integer only neural network is created in this paper, which is then accelerated by using DSP instructions to improve performance.

Keywords: Digital Signal Processor (DSP), Integer Neural Network(INN), Low Cost Neural Network, Integer Neural Network DSPImplementation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1738
3060 General Regression Neural Network and Back Propagation Neural Network Modeling for Predicting Radial Overcut in EDM: A Comparative Study

Authors: Raja Das, M. K. Pradhan

Abstract:

This paper presents a comparative study between two neural network models namely General Regression Neural Network (GRNN) and Back Propagation Neural Network (BPNN) are used to estimate radial overcut produced during Electrical Discharge Machining (EDM). Four input parameters have been employed: discharge current (Ip), pulse on time (Ton), Duty fraction (Tau) and discharge voltage (V). Recently, artificial intelligence techniques, as it is emerged as an effective tool that could be used to replace time consuming procedures in various scientific or engineering applications, explicitly in prediction and estimation of the complex and nonlinear process. The both networks are trained, and the prediction results are tested with the unseen validation set of the experiment and analysed. It is found that the performance of both the networks are found to be in good agreement with average percentage error less than 11% and the correlation coefficient obtained for the validation data set for GRNN and BPNN is more than 91%. However, it is much faster to train GRNN network than a BPNN and GRNN is often more accurate than BPNN. GRNN requires more memory space to store the model, GRNN features fast learning that does not require an iterative procedure, and highly parallel structure. GRNN networks are slower than multilayer perceptron networks at classifying new cases.

Keywords: Electrical-discharge machining, General Regression Neural Network, Back-propagation Neural Network, Radial Overcut.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3007
3059 Comparison between Beta Wavelets Neural Networks, RBF Neural Networks and Polynomial Approximation for 1D, 2DFunctions Approximation

Authors: Wajdi Bellil, Chokri Ben Amar, Adel M. Alimi

Abstract:

This paper proposes a comparison between wavelet neural networks (WNN), RBF neural network and polynomial approximation in term of 1-D and 2-D functions approximation. We present a novel wavelet neural network, based on Beta wavelets, for 1-D and 2-D functions approximation. Our purpose is to approximate an unknown function f: Rn - R from scattered samples (xi; y = f(xi)) i=1....n, where first, we have little a priori knowledge on the unknown function f: it lives in some infinite dimensional smooth function space and second the function approximation process is performed iteratively: each new measure on the function (xi; f(xi)) is used to compute a new estimate f as an approximation of the function f. Simulation results are demonstrated to validate the generalization ability and efficiency of the proposed Beta wavelet network.

Keywords: Beta wavelets networks, RBF neural network, training algorithms, MSE, 1-D, 2D function approximation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1849
3058 Application of Artificial Neural Networks for Temperature Forecasting

Authors: Mohsen Hayati, Zahra Mohebi

Abstract:

In this paper, the application of neural networks to study the design of short-term temperature forecasting (STTF) Systems for Kermanshah city, west of Iran was explored. One important architecture of neural networks named Multi-Layer Perceptron (MLP) to model STTF systems is used. Our study based on MLP was trained and tested using ten years (1996-2006) meteorological data. The results show that MLP network has the minimum forecasting error and can be considered as a good method to model the STTF systems.

Keywords: Artificial neural networks, Forecasting, Weather, Multi-layer perceptron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4290