Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network

by   Chen Li, et al.

Hyperparameter optimization is a challenging problem in developing deep neural networks. Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN). Conventional transfer CNN models are usually manually designed based on intuition. In this paper, a genetic algorithm is applied to select trainable layers of the transfer model. The filter criterion is constructed by accuracy and the counts of the trainable layers. The results show that the method is competent in this task. The system will converge with a precision of 97 classification of Cats and Dogs datasets, in no more than 15 generations. Moreover, backward inference according the results of the genetic algorithm shows that our method can capture the gradient features in network layers, which plays a part on understanding of the transfer AI models.


A Genetic Algorithm based Kernel-size Selection Approach for a Multi-column Convolutional Neural Network

Deep neural network-based architectures give promising results in variou...

Genetic CNN

The deep Convolutional Neural Network (CNN) is the state-of-the-art solu...

An Improved Genetic Algorithm and Its Application in Neural Network Adversarial Attack

The choice of crossover and mutation strategies plays a crucial role in ...

Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm

Convolutional Neural Networks (CNN) have gained great success in many ar...

REGAL: Transfer Learning For Fast Optimization of Computation Graphs

We present a deep reinforcement learning approach to optimizing the exec...

Please sign up or login with your details

Forgot password? Click here to reset