Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network
Authors:
- RenGang LiRLRenGang Li
- Xin ZhangXZXin Zhang
Preprint
Abstract
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% in the 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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Hyperparameter Optimization Using a Genetic Algorithm Considering Verification Time in a Convolutional Neural NetworkJournal of Electrical Engineering & Technology, 2020
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Undoing the Damage of Dataset Bias2012
- Tabula rasa: Model transfer for object category detection2011
- Evolutionary artificial neural networks: a reviewArtificial Intelligence Review, 2011
- What you saw is not what you get: Domain adaptation using asymmetric kernel transforms2011
- Safety in numbers: Learning categories from few examples with multi model knowledge transfer2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- A latent model of discriminative aspect2009
- A genetic algorithm for flowshop sequencingComputers & Operations Research, 1995