Comparative Study of High Speed Back- Propagation Learning Algorithms
نویسنده
چکیده
Back propagation is one of the well known training algorithms for multilayer perceptron. However the rate of convergence in back propagation learning tends to be relatively slow, which in turn makes it computationally excruciating. Over the last years many modifications have been proposed to improve the efficiency and convergence speed of the back propagation algorithm. The main emphasis of this paper is on investigating the performance of improved versions of back propagation algorithm in training the neural network. All of them are assessed on different training sets and a comparative analysis is made. Results of computer simulations with standard benchmark problems such as XOR, 3 BIT PARITY, MODIFIED XOR and IRIS are presented. The training performance of these algorithms is evaluated in terms of percentage of accuracy, and convergence speed.
منابع مشابه
Comparative Analysis of Machine Learning Algorithms with Optimization Purposes
The field of optimization and machine learning are increasingly interplayed and optimization in different problems leads to the use of machine learning approaches. Machine learning algorithms work in reasonable computational time for specific classes of problems and have important role in extracting knowledge from large amount of data. In this paper, a methodology has been employed to opt...
متن کاملA COMPARATIVE STUDY FOR THE OPTIMAL DESIGN OF STEEL STRUCTURES USING CSS AND ACSS ALGORITHMS
In this article, an Advanced Charged System Search (ACSS) algorithm is applied for the optimum design of steel structures. ACSS uses the idea of Opposition-based Learning and Levy flight to enhance the optimization abilities of the standard CSS. It also utilizes the information of the position of each charged particle in the subsequent search process to increase the convergence speed. The objec...
متن کاملOn the use of back propagation and radial basis function neural networks in surface roughness prediction
Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically, feed-forward artificial neural networks are trained with three different back propagation algorithms, ...
متن کاملAn empirical study of learning speed in back-propagation networks
Most connectionist or "neural network" learning systems use some form of the back-propagation algorithm. However, back-propagation learning is too slow for many applications, and it scales up poorly as tasks become larger and more complex. The factors governing learning speed are poorly understood. I have begun a systematic, empirical study of learning speed in backprop-like algorithms, measure...
متن کاملClassification of ECG signals using Hermite functions and MLP neural networks
Classification of heart arrhythmia is an important step in developing devices for monitoring the health of individuals. This paper proposes a three module system for classification of electrocardiogram (ECG) beats. These modules are: denoising module, feature extraction module and a classification module. In the first module the stationary wavelet transform (SWF) is used for noise reduction of ...
متن کامل