Search Results for author: Anup Sarma

Found 2 papers, 0 papers with code

Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs

no code implementations16 Sep 2021 Anup Sarma, Sonali Singh, Huaipan Jiang, Ashutosh Pattnaik, Asit K Mishra, Vijaykrishnan Narayanan, Mahmut T Kandemir, Chita R Das

By exploiting sparsity in both the forward and backward passes, speedup improvements range from 1. 68$\times$ to 3. 30$\times$ over the sparsity-agnostic baseline execution.

Image Classification object-detection +1

Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training

no code implementations NeurIPS 2021 Anup Sarma, Sonali Singh, Huaipan Jiang, Rui Zhang, Mahmut T Kandemir, Chita R Das

Recurrent Neural Networks (RNNs), more specifically their Long Short-Term Memory (LSTM) variants, have been widely used as a deep learning tool for tackling sequence-based learning tasks in text and speech.

Language Modelling Machine Translation +3

Cannot find the paper you are looking for? You can Submit a new open access paper.