research
∙
12/29/2022
Macro-block dropout for improved regularization in training end-to-end speech recognition models
This paper proposes a new regularization algorithm referred to as macro-...
share
research
∙
09/05/2020
S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima
The stochastic gradient descent (SGD) method is most widely used for dee...
research
∙
03/30/2018
Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference
As neural network algorithms show high performance in many applications,...
research
∙
02/04/2016