چکیده مقاله
In this research, we propose Tsallis entropy for deep transfer learning as an efficient and flexible method to construct a regularized classifier We improve bias problem on the Convolutional Neural Network CNN model based on statistical learning for unsupervised domain adaptation At first, Tsallis entropy on source domain has been applied to reduce loss Then, a cosine similarity is used based on K Nearest Neighbors KNN classifier to regularize CNN classifier by alleviating the error discrepancy between them A non extensive Tsallis entropy function based on KNN classifier is designed as self regularization for reducing the learning bias Moreover, the marginal distribution and the conditional distribution have simultaneously been aligned by Joint Distribution Adaptation JDA Finally, the experiments are implemented on the regularized CNN according to the traditional cross entropy loss and proposed Tsallis entropy loss The results show that regularized deep transfer learning based on Tsallis entropy is effective and robust for domain adaptation problems, and it has less loss than state of the art domain adaptation methods to detect unreliable samples
کلیدواژهها
نویسندگان
Zahra Ramezani
Department of Statistics, University of Mazandaran, Babolsar, Iran
Ahmad Pourdarvish
Department of Statistics, University of Mazandaran, Babolsar, Iran
شیوه ارجاع
Ramezani, Zahra and Pourdarvish, Ahmad,1400,Tsallis Entropy for Deep Transfer Learning and Domain Adaptation,Fourth International Conference on Soft Computing
ارائهشده در
مجموعه مقالات چهارمین کنفرانس بین المللی محاسبات نرم8 دی 1400