A Novel approach in Classification by Evolutionary Neural Networks
Publish place: International Journal of Mechatronics, Electrical and Computer Technology، Vol: 4، Issue: 10
Publish Year: 1393
نوع سند: مقاله ژورنالی
زبان: English
View: 436
This Paper With 20 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_IJMEC-4-10_005
تاریخ نمایه سازی: 16 فروردین 1395
Abstract:
Artificial neural network is an interconnected group of natural or artificial neurons that uses a mathematical or computational model for information processing based on a connectionist approach to computation. Neural network optimization based on three basic parameters topology, weights and the learning rate. The over fitting is a problem in NN and it produced when discordant input data with before data. We introduce optimal method for solving this problem. In this paper genetic algorithm with mutation and crossover operators by two approaches on coding solutions by optimizing the weights and network structure is encoded. Also used the simulated annealing by this idea that coordination between mutation rate in GA and Temperature in SA is suitable for grid of local optimum, Plateau and fast learning.
Keywords:
Authors
Dadmehr Rahbari
Artificial Intelligence Group of Mashhad Azad University, Mashhad, Iran