Zobrazeno 1 - 10
of 402
pro vyhledávání: '"Mandal, Sumit"'
Autor:
Nagil, Praveen, Mandal, Sumit K.
Assistive technology for visually impaired individuals is extremely useful to make them independent of another human being in performing day-to-day chores and instill confidence in them. One of the important aspects of assistive technology is outdoor
Externí odkaz:
http://arxiv.org/abs/2406.15864
Network-on-Chip (NoC) congestion builds up during heavy traffic load and cripples the system performance by stalling the cores. Moreover, congestion leads to wasted link bandwidth due to blocked buffers and bouncing packets. Existing approaches throt
Externí odkaz:
http://arxiv.org/abs/2302.12779
Autor:
Mandal, Sumit K., Krishnan, Gokul, Goksoy, A. Alper, Nair, Gopikrishnan Ravindran, Cao, Yu, Ogras, Umit Y.
Graph convolutional networks (GCNs) have shown remarkable learning capabilities when processing graph-structured data found inherently in many application areas. GCNs distribute the outputs of neural networks embedded in each vertex over multiple ite
Externí odkaz:
http://arxiv.org/abs/2205.07311
Autor:
Tushar, Shariful Islam, Anik, Habibur Rahman, Uddin, Md Mazbah, Mandal, Sumit, Mohakar, Vijay, Rai, Smriti, Sharma, Suraj
Publikováno v:
In Carbohydrate Polymers 1 September 2024 339
Autor:
Mandal, Sumit K., Tong, Jie, Ayoub, Raid, Kishinevsky, Michael, Abousamra, Ahmed, Ogras, Umit Y.
Fast and accurate performance analysis techniques are essential in early design space exploration and pre-silicon evaluations, including software eco-system development. In particular, on-chip communication continues to play an increasingly important
Externí odkaz:
http://arxiv.org/abs/2108.09534
Autor:
Krishnan, Gokul, Mandal, Sumit K., Pannala, Manvitha, Chakrabarti, Chaitali, Seo, Jae-sun, Ogras, Umit Y., Cao, Yu
In-memory computing (IMC) on a monolithic chip for deep learning faces dramatic challenges on area, yield, and on-chip interconnection cost due to the ever-increasing model sizes. 2.5D integration or chiplet-based architectures interconnect multiple
Externí odkaz:
http://arxiv.org/abs/2108.08903
Neural architecture search (NAS) is a promising technique to design efficient and high-performance deep neural networks (DNNs). As the performance requirements of ML applications grow continuously, the hardware accelerators start playing a central ro
Externí odkaz:
http://arxiv.org/abs/2108.00568
Autor:
Krishnan, Gokul, Mandal, Sumit K., Chakrabarti, Chaitali, Seo, Jae-sun, Ogras, Umit Y., Cao, Yu
With the widespread use of Deep Neural Networks (DNNs), machine learning algorithms have evolved in two diverse directions -- one with ever-increasing connection density for better accuracy and the other with more compact sizing for energy efficiency
Externí odkaz:
http://arxiv.org/abs/2107.02358