2 papers
cs.LG2019
Layer Dynamics of Linearised Neural Nets
Saurav Basu, Koyel Mukherjee, Shrihari Vasudevan
Despite the phenomenal success of deep learning in recent years, there remains a gap in understanding the fundamental mechanics of neural nets. More research is focussed on handcra…
cs.LG2018
Dynamic learning rate using Mutual Information
Shrihari Vasudevan
This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the…