6 citations · 19 across the 10 of their papers we have counts for
3 papers · 1 filter
Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs
Anup Sarma, Sonali Singh, Huaipan Jiang +5
Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies, achieving high accuracy on computer vision workloads such as i…
Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training
Anup Sarma, Sonali Singh, Huaipan Jiang +3
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…
Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud
Jashwant Raj Gunasekaran, Cyan Subhra Mishra, Prashanth Thinakaran +2
With a growing demand for adopting ML models for a varietyof application services, it is vital that the frameworks servingthese models are capable of delivering highly accurate pre…