Filters








1 Hit in 11.1 sec

A Survey of Deep Active Learning [article]

Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
2021 arXiv   pre-print
This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples. Therefore, early AL is difficult to reflect the value it deserves.  ...  Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model learns how to extract high-quality features.  ...  In Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part II (Lecture  ... 
arXiv:2009.00236v2 fatcat:zuk2doushzhlfaufcyhoktxj7e