27,713 Hits in 6.2 sec

Neural Network Modeling for Evaluating Sodium Temperature of Intermediate Heat Exchanger of Fast Breeder Reactor

Subhra Rani Patra, R. Jehadeesan, S. Rajeswari, Indranil Banerjee, S. A. V Satya Murty, G. Padmakumar, M. Sai Baba
2012 Advances in Computing  
The back propagation (BP) algorithm is used for training the network.  ...  Further a model based on Radial Basis Function (RBF) neural network is developed and trained and the results are compared with standard back propagation algorithm.  ...  Sri S.C Chetal, Director, IGCAR, Kalpakkam for his constant support and guidance for this project.  ... 
doi:10.5923/ fatcat:asgm25sj7nfehjks25swhsgcqi

Optimal Parameter Selection Using Three-term Back Propagation Algorithm for Data Classification

Nazri Mohd Nawi, Nurmahiran Muhammad Zaidi, Noorhamreeza Abdul Hamid, Muhammad Zubair Rehman, Azizul Azhar Ramli, Shahreen Kasim
2017 International Journal on Advanced Science, Engineering and Information Technology  
The back propagation (BP) algorithm is the most popular supervised learning method for multi-layered feed forward Neural Network.  ...  Therefore, to resolve the inherent problems of BP algorithm, this paper proposed BPGD-A3T algorithm where the approach introduces three adaptive parameters which are gain, momentum and learning rate in  ...  Yu and Liu [15] , proposed a back propagation algorithm with adaptive learning rate and momentum.  ... 
doi:10.18517/ijaseit.7.4-2.3387 fatcat:kg452yosarextdtka2l4kinpdy

An Improved Learning Algorithm Based On The Conjugate Gradient Method For Back Propagation Neural Networks

N. M. Nawi, M. R. Ransing, R. S. Ransing
2008 Zenodo  
The conjugate gradient optimization algorithm usually used for nonlinear least squares is presented and is combined with the modified back propagation algorithm yielding a new fast training multilayer  ...  The proposed method improved the training efficiency of back propagation algorithm by adaptively modifying the initial search direction.  ...  Second, the convergence rate of back-propagation is still too slow even if learning can be achieved. in the algorithm such as the learning rate and the momentum.  ... 
doi:10.5281/zenodo.1328444 fatcat:ha4kcihvjrfzvfhcafuogetxj4

Neural Network Based Numerical digits Recognization using NNT in Matlab

Amritpal kaur, Madhavi Arora
2013 International Journal of Computer Science & Engineering Survey  
The features of the number given by the user are extracted and compared with the feature database and the recognized number is displayed.  ...  Artificial neural networks are models inspired by human nervous system that is capable of learning. One of the important applications of artificial neural network is character Recognition.  ...  ADAPTIVE LEARNING RATE The back propagation algorithms are basically of two types, gradient descent and gradient descent with momentum.  ... 
doi:10.5121/ijcses.2013.4502 fatcat:s75oacf55bgjbc6nryrbchse4i

Neural Networks With Random Letter Codes For Text-To-Phoneme Mapping And Small Training Dictionary

J. Astola, Eniko Bilcu
2006 Zenodo  
Also three types of encoding vectors for the input letters are analyzed and two training algorithms: the error back-propagation with momentum and fixed learning rate and the error back-propagation with  ...  The training algorithm that used a fixed learning rate was the error back-propagation with momentum (see [1] , [2] and [10] for more details).  ... 
doi:10.5281/zenodo.53235 fatcat:rbowqltpandchccgqtxhzvz42e

Towards Food Security through Artificial Neural Network

Pratibha Phaiju
2019 Journal of Science and Engineering  
The error generated is back propagated in order to adjust the weights of neural network. Images of the diseased leaves are identified with accuracy.  ...  The disease identification is achieved through Image Processing technique and Back Propagation Neural Network. Features of images are extracted through binning pixels into eight Attribute Bins.  ...  Adapting the learning rate requires some changes in the back propagation algorithm.  ... 
doi:10.3126/jsce.v6i0.23968 fatcat:lxugug4dzbdmzkw6b7me7w3j5q

A New Bat Based Back-Propagation (BAT-BP) Algorithm [chapter]

Nazri Mohd. Nawi, Muhammad Zubair Rehman, Abdullah Khan
2014 Advances in Intelligent Systems and Computing  
convergence rate.  ...  The performance of the proposed Bat based Back-Propagation (Bat-BP) algorithm is compared with Artificial Bee Colony using BPNN algorithm (ABC-BP) and simple BPNN algorithm.  ...  Artificial Bee Colony with Back-Propagation (ABC-BP) algorithm [16] [17] , and 3.  ... 
doi:10.1007/978-3-319-01857-7_38 fatcat:zdtoo3e2wjhqvlcrxs27fvctve

On Training Of Feed Forward Neural Networks

Baghdad Science Journal
2007 Baghdad Science Journal  
In all of these algorithms we use the gradient of the performance function, energy function, to determine how to adjust the weights such that the performance function is minimized, where the back propagation  ...  algorithm has been used to increase the speed of training.  ...  training. 1.Variable Learning Rate With standard gradient descent, the learning rate is held constant through out training.  ... 
doi:10.21123/bsj.4.1.158-164 fatcat:jd3pxgmkrveprnkcwakgijsrr4

Second Order Learning Algorithm for Back Propagation Neural Networks

Nazri Mohd Nawi, Noorhamreeza Abdul Hamid, Noor Azah Samsudin, Mohd Amin Mohd Yunus, Mohd Firdaus Ab Aziz
2017 International Journal on Advanced Science, Engineering and Information Technology  
The simulation results clearly demonstrate that the proposed method significantly improves the convergence rate significantly faster the learning process of the general back propagation algorithm because  ...  The new procedure computes and improves the search direction along the negative gradient by introducing the 'gain' value of the activation functions and calculating the negative gradient on an error with  ...  (a) (b) Fig. 4 Output of the neural network training to learn a sine curve with and without using the adaptive gain in back propagation algorithm (a), and convergence speed for the sine function with  ... 
doi:10.18517/ijaseit.7.4.1956 fatcat:sy7qta7oufa37ld6cmpcohhvdu

Countering the Problem of Oscillations in Bat-BP Gradient Trajectory by Using Momentum [chapter]

Nazri Mohd. Nawi, M. Z. Rehman, Abdullah Khan
2013 Lecture Notes in Electrical Engineering  
Previously, a meta-heuristic search algorithm called Bat was proposed to train BPNN to achieve fast convergence in the neural network.  ...  The performance of the modified Bat-BP algorithm is compared with simple Bat-BP algorithm on XOR and OR datasets.  ...  learning rate.  ... 
doi:10.1007/978-981-4585-18-7_12 fatcat:nscw5krh7jesxgypcyfzziy7hq

Adaptive packet equalization for indoor radio channel using multilayer neural networks

Po-Rong Chang, Bao-Fuh Yeh, Chih-Chiang Chang
1994 IEEE Transactions on Vehicular Technology  
In this paper, another fast packet-wise training algorithm with better convergence properties is derived on the basis of a recursive least-squares (RLS) routine.  ...  To tackle this difficulty, a neural-based DFE is proposed to deal with the complex QAM signal over the complex-valued fading multipath radio channel without performing time-consuming complex-valued back-propagation  ...  Since the gradient descent algorithm is globally convergent, this implies that the batch back-propagation algorithm is also globally convergent.  ... 
doi:10.1109/25.312768 fatcat:ocni6gyg5nbilmqyypnt2xtn3m

A microarray gene expression data classification using hybrid back propagation neural network

M. Vimaladevi, B. Kalaavathi
2014 Genetika  
This technical note applies hybrid models of Back Propagation Neural networks (BPN) and fast Genetic Algorithms (GA) to estimate the feature selection in gene expression data.  ...  The back propagation method may execute the function of collaborate multiple parties. In existing method, collaborative learning is limited and it considers only two parties.  ...  The hybrid algorithm of Back Propagation and Fast Genetic Algorithm will be designed to train and test the network.  ... 
doi:10.2298/gensr1403013v fatcat:g2kxefiqqfedbp6of5ohhdr4wy

A cloning approach to classifier training

M.A. Al-Alaoui, R. Mouci, M.M. Mansour, R. Ferzli
2002 IEEE transactions on systems, man and cybernetics. Part A. Systems and humans  
It is also shown that the application of the Al-Alaoui algorithm to multilayer neural networks speeds up the convergence of the back-propagation algorithm.  ...  The algorithm was originally developed for linear classifiers. In this paper, the algorithm is extended to multilayer neural networks which may be used as nonlinear classifiers.  ...  In Section IV, the current standard back-propagation algorithm (designated as BP), which includes momentum and an adaptive learning rate, is compared with the modified standard back-propagation algorithm  ... 
doi:10.1109/tsmca.2002.807035 fatcat:6xxgjniauncgngoetu5odqrpc4

Machine Learning with Resilient Propagation in Quaternionic Domain

Sushil Kumar, Bipin Tripathi
2017 International Journal of Intelligent Engineering and Systems  
It achieves significantly faster learning over quaternionic domain back propagation (ℍ-BP) algorithm.  ...  The slow convergence problem of back-propagation algorithm has been well combated by ℍ-RPROP. It has always demonstrated drastic reduction in the training cycles.  ...  Inferences and discussions In this paper, we propose a fast and efficient learning algorithm ℍ-RPROP (resilient propagation in quaternionic domain); and its superiority over back-propagation algorithm  ... 
doi:10.22266/ijies2017.0831.22 fatcat:zfeqzk754fgq7dwpts5w6iqjya

Autism Spectrum Diagnosis using Adaptive Learning Algorithm for Multiple MLP Classifier

Faemeh Safara1 And Fatemeh Safara 1*
2021 Zenodo  
In addition, learning rate was constant on mot of the previous studies. In this paper, we used adaptive learning rate with the back propagation learning algorithm.  ...  An adaptive learning rate algorithm is used to improve the convergence rate of the back-propagation as well.  ... 
doi:10.5281/zenodo.5188620 fatcat:rubklfngsndrhdbxxveyuvle7e
« Previous Showing results 1 — 15 out of 27,713 results