Optimizing neural-network learning rate by using a genetic algorithm with per-epoch mutations

2016 ◽  
Author(s):  
Yasusi Kanada
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Learning Rate ◽  
Neural Network Learning ◽  
Network Learning

scholarly journals PENENTUAN PARAMETER LEARNING RATE SELAMA PEMBELAJARAN JARINGAN SYARAF TIRUAN BACKPROPAGATION MENGGUNAKAN ALGORITMA GENETIKA

2020 ◽  
Vol 14 (2) ◽  
pp. 202-212
Author(s):  
Ade chandra Saputra
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Fitness Function ◽  
Learning Rate ◽  
Local Minima ◽  
Rate Parameter ◽  
Neural Network Learning ◽  
Value Of Learning ◽  
Backpropagation Learning

One of the weakness in backpropagation Artificial neural network(ANN) is being stuck in local minima. Learning rate parameter is an important parameter in order to determine how fast the ANN Learning. This research is conducted to determine a method of finding the value of learning rate parameter using a genetic algorithm when neural network learning stops and the error value is not reached the stopping criteria or has not reached the convergence. Genetic algorithm is used to determine the value of learning rate used is based on the calculation of the fitness function with the input of the ANN weights, gradient error, and bias. The calculation of the fitness function will produce an error value of each learning rate which represents each candidate solutions or individual genetic algorithms. Each individual is determined by sum of squared error value. One with the smallest SSE is the best individual. The value of learning rate has chosen will be used to continue learning so that it can lower the value of the error or speed up the learning towards convergence. The final result of this study is to provide a new solution to resolve the problem in the backpropagation learning that often have problems in determining the learning parameters. These results indicate that the method of genetic algorithms can provide a solution for backpropagation learning in order to decrease the value of SSE when learning of ANN has been static in large error conditions, or stuck in local minima

Product Form Design Based on Neural Network and Genetic Algorithm

2011 ◽  
Vol 460-461 ◽  
pp. 26-31
Author(s):  
Cheng Yang ◽  
Qun Wu ◽  
Jian Feng Wu
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Product Innovation ◽  
Evolutionary Process ◽  
Similar Model ◽  
Neural Network Learning ◽  
Network Learning ◽  
Form Design ◽  
Product Form Design

A method of product innovation design was presented. Based on product gene and interactive genetic algorithm, designs of products evolved into new programs, with which make customers be satisfied. In the evolutionary process, a similar model, which was made by neural network learning, was used to evaluate the fitness of products. This method not only shortened the time which was taken in the process of evolution, but also to avoid the decline in the quality of evaluations which resulted from the mental fatigue of user, and ensured the accuracy of the solution.

Application of a genetic algorithm to optimize BP neural networks

2020 ◽  
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Bp Neural Network ◽  
Local Minimum ◽  
Network Performance ◽  
Learning Algorithm ◽  
Simulation Data ◽  
Neural Network Learning ◽  
Network Learning ◽  
Fast Convergence Rate

A genetic algorithm is proposed to us to prevent a local minimum defect when using the BP neural network learning algorithm. The genetic algorithm is first used to optimize the weight and threshold of the BP neural network, and then obtained values are used to optimize the BP neural network. Optimized network performance is estimated using simulation data. The results of numerical simulations show that the BP neural network optimized by the genetic algorithm can effectively eliminate a local minimum defect, which is easy to find in the original BP neural network, and has the advantages of fast convergence rate and high accuracy. Keywords BP neural network; genetic algorithm; local minimum defect; optimization

Sign in / Sign up

Export Citation Format

Share Document