1. Variational information distillation for knowledge transfer;Ahn,2019
2. Large scale distributed neural network training through online distillation;Anil,2018
3. Enhancing deep learning sentiment analysis with ensemble techniques in social applications;Araque;Expert Systems with Applications,2017
4. Ba, J., & Caruana, R. (2014). Do deep nets really need to be deep? In Advances in neural information processing systems 27 (pp. 2654–2662).
5. Model compression;Buciluaˇ,2006