Spremljaj
Sanchari Sen
Sanchari Sen
Staff Research Scientist, IBM T. J. Watson Research Center
Preverjeni e-poštni naslov na ibm.com
Naslov
Navedeno
Navedeno
Leto
RaPiD: AI Accelerator for Ultra-low Precision Training and Inference
S Venkataramani, V Srinivasan, W Wang, S Sen, J Zhang, A Agrawal, ...
2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture …, 2021
962021
EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks
S Sen, B Ravindran, A Raghunathan
2020 International Conference on Learning Representations (ICLR), 2020
832020
Approximate computing for spiking neural networks
S Sen, S Venkataramani, A Raghunathan
2017 Design, Automation & Test in Europe Conference & Exhibition (DATE), 193-198, 2017
692017
Approximate Computing for Long Short Term Memory (LSTM) Neural Networks
S Sen, A Raghunathan
IEEE Transactions on Computer-Aided Design of Integrated Circuits and …, 2018
592018
SparCE: Sparsity Aware General-Purpose Core Extensions to Accelerate Deep Neural Networks
S Sen, S Jain, S Venkataramani, A Raghunathan
IEEE Transactions on Computers 68 (6), 912-925, 2018
572018
A Programmable Event-driven Architecture for Evaluating Spiking Neural Networks
A Roy, S Venkataramani, N Gala, S Sen, K Veezhinathan, ...
2017 IEEE/ACM International Symposium on Low Power Electronics and Design …, 2017
302017
Dynamic Spike Bundling for Energy-Efficient Spiking Neural Networks
S Krithivasan, S Sen, S Venkataramani, A Raghunathan
2019 IEEE/ACM International Symposium on Low Power Electronics and Design …, 2019
242019
Deep Compression of Pre-trained Transformer Models
N Wang, CCC Liu, S Venkataramani, S Sen, CY Chen, K El Maghraoui, ...
Advances in Neural Information Processing Systems 35, 14140-14154, 2022
222022
Accelerating DNN Training Through Selective Localized Learning
S Krithivasan, S Sen, S Venkataramani, A Raghunathan
Frontiers in Neuroscience 15, 759807, 2022
82022
Value Similarity Extensions for Approximate Computing in General-Purpose Processors
Y Kim, S Venkataramani, S Sen, A Raghunathan
2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), 481-486, 2021
82021
Sparsity Turns Adversarial: Energy and Latency Attacks on Deep Neural Networks
S Krithivasan, S Sen, A Raghunathan
IEEE Transactions on Computer-Aided Design of Integrated Circuits and …, 2020
82020
Efficiency attacks on spiking neural networks
S Krithivasan, S Sen, N Rathi, K Roy, A Raghunathan
Proceedings of the 59th ACM/IEEE Design Automation Conference, 373-378, 2022
72022
A Case for Generalizable DNN Cost Models for Mobile Devices
V Ganesan, S Selvam, S Sen, P Kumar, A Raghunathan
2020 IEEE International Symposium on Workload Characterization (IISWC), 169-180, 2020
62020
Optimizing transformers with approximate computing for faster, smaller and more accurate NLP models
A Nagarajan, S Sen, JR Stevens, A Raghunathan
62020
Sparsity-Aware Caches to Accelerate Deep Neural Networks
V Ganesan, S Sen, P Kumar, N Gala, K Veezhinathan, A Raghunathan
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 85-90, 2020
62020
AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models
A Nagarajan, S Sen, JR Stevens, A Raghunathan
2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022
42022
RaPiD: AI Accelerator for Ultra-low Precision Training and Inference. In 2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA). 153–166
S Venkataramani, V Srinivasan, W Wang, S Sen, J Zhang, A Agrawal, ...
Academic Search Academic Search Digital Library Digital Library, 2021
42021
Efficacy of pruning in ultra-low precision DNNs
S Sen, S Venkataramani, A Raghunathan
2021 IEEE/ACM International Symposium on Low Power Electronics and Design …, 2021
32021
Probabilistic spike propagation for efficient hardware implementation of spiking neural networks
A Nallathambi, S Sen, A Raghunathan, N Chandrachoodan
Frontiers in Neuroscience 15, 694402, 2021
32021
14.1 A Software-Assisted Peak Current Regulation Scheme to Improve Power-Limited Inference Performance in a 5nm AI SoC
M Kar, J Silberman, S Venkataramani, V Srinivasan, B Fleischer, J Rubin, ...
2024 IEEE International Solid-State Circuits Conference (ISSCC) 67, 254-256, 2024
22024
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–20