EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks

Apr 21, 2020
Sanchari Sen, Balaraman Ravindran, Anand Raghunathan

* Published as a conference paper at ICLR 2020 

  Access Model/Code and Paper
Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks

Mar 05, 2020
Sourjya Roy, Priyadarshini Panda, Gopalakrishnan Srinivasan, Anand Raghunathan


  Access Model/Code and Paper
TxSim:Modeling Training of Deep Neural Networks on Resistive Crossbar Systems

Feb 25, 2020
Sourjya Roy, Shrihari Sridharan, Shubham Jain, Anand Raghunathan


  Access Model/Code and Paper
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks

Feb 23, 2020
Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan, Kaushik Roy

* 10 pages, 6 figures, 5 tables 

  Access Model/Code and Paper
TiM-DNN: Ternary in-Memory accelerator for Deep Neural Networks

Sep 30, 2019
Shubham Jain, Sumeet Kumar Gupta, Anand Raghunathan


  Access Model/Code and Paper
TiM-DNN: Ternary in Memory accelerator for Deep Neural Networks

Sep 15, 2019
Shubham Jain, Sumeet Kumar Gupta, Anand Raghunathan


  Access Model/Code and Paper
Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing

Oct 01, 2018
Athindran Ramesh Kumar, Balaraman Ravindran, Anand Raghunathan


  Access Model/Code and Paper
Rx-Caffe: Framework for evaluating and training Deep Neural Networks on Resistive Crossbars

Aug 31, 2018
Shubham Jain, Abhronil Sengupta, Kaushik Roy, Anand Raghunathan


  Access Model/Code and Paper
SparCE: Sparsity aware General Purpose Core Extensions to Accelerate Deep Neural Networks

Nov 29, 2017
Sanchari Sen, Shubham Jain, Swagath Venkataramani, Anand Raghunathan


  Access Model/Code and Paper
DyVEDeep: Dynamic Variable Effort Deep Neural Networks

Apr 04, 2017
Sanjay Ganapathy, Swagath Venkataramani, Balaraman Ravindran, Anand Raghunathan


  Access Model/Code and Paper
Energy-Efficient Object Detection using Semantic Decomposition

Sep 20, 2016
Priyadarshini Panda, Swagath Venkataramani, Abhronil Sengupta, Anand Raghunathan, Kaushik Roy

* 10 pages, 13 figures, 3 algorithms, Submitted to IEEE TVLSI(Under Review) 

  Access Model/Code and Paper
Multiplier-less Artificial Neurons Exploiting Error Resiliency for Energy-Efficient Neural Computing

Feb 27, 2016
Syed Shakib Sarwar, Swagath Venkataramani, Anand Raghunathan, Kaushik Roy

* In Design, Automation & Test in Europe Conference & Exhibition (DATE), 2016, pp. 145-150 
* Accepted in Design, Automation and Test in Europe 2016 conference (DATE-2016) 

  Access Model/Code and Paper