Genetic Algorithms for Evolving Deep Neural Networks

Abstract

In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.

References in corpus (1)

• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (13)

• Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges
• Negatively Correlated Search
• Gradient Descent based Optimization Algorithms for Deep Learning Models Training
• Texture Classification in Extreme Scale Variations using GANet
• Automatic Design of Artificial Neural Networks for Gamma-Ray Detection
• GADAM: Genetic-Evolutionary ADAM for Deep Neural Network Optimization
• Towards the Evolution of Multi-Layered Neural Networks: A Dynamic Structured Grammatical Evolution Approach
• Deep Learning Based Superconductivity: Prediction and Experimental Tests
• Learnability and Robustness of Shallow Neural Networks Learned With a Performance-Driven BP and a Variant PSO For Edge Decision-Making
• GACNN: Training Deep Convolutional Neural Networks with Genetic Algorithm
• Neuroevolution in Deep Learning: The Role of Neutrality
• Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels
• Training Stacked Denoising Autoencoders for Representation Learning