Urmăriți
Soumendu Kumar Ghosh
Soumendu Kumar Ghosh
Deep Learning HW Engineer, Advanced Architecture Research, Intel Client AI
Adresă de e-mail confirmată pe intel.com
Titlu
Citat de
Citat de
Anul
Power efficient event detection scheme in wireless sensor networks for railway bridge health monitoring system
SK Ghosh, M Suman, R Datta, PK Biswas
2014 IEEE International Conference on Advanced Networks and …, 2014
192014
Approximate inference systems (axis) end-to-end approximations for energy-efficient inference at the edge
SK Ghosh, A Raha, V Raghunathan
Proceedings of the ACM/IEEE International Symposium on Low Power Electronics …, 2020
132020
Special session: Approximate TinyML systems: Full system approximations for extreme energy-efficiency in intelligent edge devices
A Raha, S Ghosh, D Mohapatra, DA Mathaikutty, R Sung, C Brick, ...
2021 IEEE 39th International Conference on Computer Design (ICCD), 13-16, 2021
82021
Efficient hardware acceleration of emerging neural networks for embedded machine learning: An industry perspective
A Raha, R Sung, S Ghosh, PK Gupta, DA Mathaikutty, UI Cheema, ...
Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing …, 2023
42023
Energy-efficient approximate edge inference systems
SK Ghosh, A Raha, V Raghunathan
ACM Transactions on Embedded Computing Systems 22 (4), 1-50, 2023
42023
Impact of mismatch losses arising in crystalline and amorphous silicon PV modules-An Indian experience
P Paul, SK Ghosh, K Ghosh, D Mukherjee
2011 World Congress on Sustainable Technologies (WCST), 153-155, 2011
32011
Railway bridge health monitoring system using smart wireless sensor network
SD Velagandula, N Dhang, R Datta, SK Ghosh, S Maroju
Proceedings of the 10th ACM Conference on Security and Privacy in Wireless …, 2017
22017
CEEDS: a cost effective event detection system for energy efficient railway bridge monitoring with wireless sensor network
SK Ghosh, S Maroju, R Datta, PK Biswas
EAI Endorsed Transactions on Future Internet 3 (8), 2016
22016
PArtNNer: Platform-Agnostic Adaptive Edge-Cloud DNN Partitioning for Minimizing End-to-End Latency
SK Ghosh, A Raha, V Raghunathan, A Raghunathan
ACM Transactions on Embedded Computing Systems 23 (1), 1-38, 2024
12024
HARVEST: Towards Efficient Sparse DNN Accelerators using Programmable Thresholds
SK Ghosh, S Kundu, A Raha, DA Mathaikutty, V Raghunathan
2024 37th International Conference on VLSI Design and 2024 23rd …, 2024
12024
FlexNN: A Dataflow-aware Flexible Deep Learning Accelerator for Energy-Efficient Edge Devices
A Raha, DA Mathaikutty, SK Ghosh, S Kundu
arXiv preprint arXiv:2403.09026, 2024
2024
Towards Energy-Efficient Collaborative Inference Using Multi-System Approximations
A Das, SK Ghosh, A Raha, V Raghunathan
IEEE Internet of Things Journal, 2024
2024
Pruning activations and weights of neural networks with programmable thresholds
SK Ghosh, S Kundu, A Raha, DA Mathaikutty
US Patent App. 18/453,715, 2023
2023
Approximating activation functions with taylor series
UI Cheema, DA Mathaikutty, A Raha, D Kondru, RJH Sung, SK Ghosh
US Patent App. 18/346,992, 2023
2023
ENERGY EFFICIENT EDGE INFERENCE SYSTEMS
SK Ghosh
Purdue University Graduate School, 2023
2023
Dynamic uncompression for channel-separable operation in neural network
A Raha, DA Mathaikutty, RJH Sung, UI Cheema, D Kondru, SK Ghosh
US Patent App. 18/184,921, 2023
2023
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–16