Neural Network Hyperparameter Tuning based on Improved Genetic Algorithm
Authors:
Open Access
- 23 October 2019
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 17-24
Abstract
In this paper, based on the structural characteristics of neural networks, a series of improvements have been made to traditional genetic algorithms. The algorithm is used to optimize a series of hyper-parameters in the fully connected neural network, and to find the near-global optimal combination of hyper-parameters. In the case of using MNIST data set and 20 rounds of model training, the algorithm is used to optimize the fully connected neural network. Experiments show that when the population evolves to 30 generations, the accuracy of the model can reach 98.81%, which is higher than 98.4% of the official sample model. This shows that the algorithm has played a certain role in the super-parameter optimization of the neural network.Keywords
Funding Information
- Fujian science technology foundation (2019H021)
- Xiamen Municipal science and technology foundation (3502Z20173027, 3502Z20173028)
This publication has 3 references indexed in Scilit:
- Efficient Hyperparameter Tuning with Grid Search for Text Categorization using kNN Approach with BM25 SimilarityOpen Computer Science, 2019
- Google Vizier2017
- RSTensorFlow2017