Home About us Contact
|
Home About us Contact | ||
|
|
||
Backpropagation Algorithm (backpropagation + algorithm)
Selected AbstractsAn efficient concurrent implementation of a neural network algorithmCONCURRENCY AND COMPUTATION: PRACTICE & EXPERIENCE, Issue 12 2006R. Andonie Abstract The focus of this study is how we can efficiently implement the neural network backpropagation algorithm on a network of computers (NOC) for concurrent execution. We assume a distributed system with heterogeneous computers and that the neural network is replicated on each computer. We propose an architecture model with efficient pattern allocation that takes into account the speed of processors and overlaps the communication with computation. The training pattern set is distributed among the heterogeneous processors with the mapping being fixed during the learning process. We provide a heuristic pattern allocation algorithm minimizing the execution time of backpropagation learning. The computations are overlapped with communications. Under the condition that each processor has to perform a task directly proportional to its speed, this allocation algorithm has polynomial-time complexity. We have implemented our model on a dedicated network of heterogeneous computers using Sejnowski's NetTalk benchmark for testing. Copyright © 2005 John Wiley & Sons, Ltd. [source] Using a neural network in the software testing processINTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 1 2002Meenakshi Vanmali Software testing forms an integral part of the software development life cycle. Since the objective of testing is to ensure the conformity of an application to its specification, a test "oracle" is needed to determine whether a given test case exposes a fault or not. Using an automated oracle to support the activities of human testers can reduce the actual cost of the testing process and the related maintenance costs. In this paper, we present a new concept of using an artificial neural network as an automated oracle for a tested software system. A neural network is trained by the backpropagation algorithm on a set of test cases applied to the original version of the system. The network training is based on the "black-box" approach, since only inputs and outputs of the system are presented to the algorithm. The trained network can be used as an artificial oracle for evaluating the correctness of the output produced by new and possibly faulty versions of the software. We present experimental results of using a two-layer neural network to detect faults within mutated code of a small credit approval application. The results appear to be promising for a wide range of injected faults. ? 2002 John Wiley & Sons, Inc. [source] EXPERIMENTAL AND NEURAL NETWORK PREDICTION OF THE PERFORMANCE OF A SOLAR TUNNEL DRIER FOR DRYING JACKFRUIT BULBS AND LEATHERJOURNAL OF FOOD PROCESS ENGINEERING, Issue 6 2005B.K. BALA ABSTRACT This article presents the field performance of a solar tunnel drier for drying jackfruit bulbs and leather. The drier consists of a transparent plastic-covered flat-plate collector and a drying tunnel connected in series to supply hot air directly into the drying tunnel using two direct-current fans operated by a photovoltaic module. The drier has a loading capacity of 120,150 kg of fruits. Sixteen experimental runs were conducted for drying jackfruit bulbs and leather (eight runs each). The use of a solar tunnel drier led to a considerable reduction in drying time and dried products of better quality in comparison to products dried under the sun. A multilayered neural network approach was used to predict the performance of the solar tunnel drier. Using solar drying data of jackfruit bulbs and leather, the model has been trained using backpropagation algorithm. The prediction of the performance of the drier was found to be excellent after it was adequately trained. It can be used to predict the potential of the drier for different locations, and can also be used in a predictive optimal control algorithm. [source] Adaptive neuro-fuzzy inference system for computing patch radius of circular microstrip antennasMICROWAVE AND OPTICAL TECHNOLOGY LETTERS, Issue 8 2006Kerim Guney Abstract A new method based on the adaptive neuro-fuzzy inference system (ANFIS) is presented to calculate accurately the patch radius of circular microstrip antennas (MSAs). ANFIS combines the benefits of artificial neural networks (ANNs) and fuzzy inference systems (FISs) in a single model. A hybrid learning algorithm based on the least-squares method (LSM) and the backpropagation algorithm is used to identify the parameters of ANFIS. The results of ANFIS are in very good agreement with the experimental results reported elsewhere. © 2006 Wiley Periodicals, Inc. Microwave Opt Technol Lett 48: 1606,1610, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.21695 [source] How to optimize the TS-fuzzy knowledge base to achieve desired performances: Accuracy and robustnessOPTIMAL CONTROL APPLICATIONS AND METHODS, Issue 1 2008A. Soukkou Abstract Designing an effective criterion/learning to find the best rule and optimal structure is a major problem in the design process of fuzzy neural controller. In this paper, we introduce a new robust model of Takagi Sugeno fuzzy logic controller. A hybrid learning algorithm, called hybrid approach to fuzzy supervised learning (HAFSL), which combines the genetic algorithm (GA) and gradient descent technique (GD) is proposed for constructing an efficient and robust fuzzy neural network controller (FNNC). Two phases of design and learning process are presented in this work. A GA is used for finding near optimal structure/parameters of the FNNC that minimizes the number of rules (initialization procedure). The second stage of learning algorithm uses the backpropagation algorithm based on GD method to fine tune the consequent parameters of the controller. The genes of chromosome are arranged into two parts, the first part contains the control genes (the certainty factors) and the second part contains the parameters genes that representing the fuzzy knowledge base. The effectiveness of this chromosome formulation enables the fuzzy sets and rules to be optimally reduced. The performances of the HAFSL are compared to these found by the traditional PI with genetic optimization (GA-PI). Simulations demonstrate that the proposed HAFSL and GA-PI algorithms have good generalization capabilities and robustness on the water bath temperature control system. Copyright © 2007 John Wiley & Sons, Ltd. [source] | |||||||||||||