scispace - formally typeset
S

Saibal Mukhopadhyay

Researcher at Georgia Institute of Technology

Publications -  432
Citations -  10232

Saibal Mukhopadhyay is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Computer science & CMOS. The author has an hindex of 40, co-authored 381 publications receiving 8814 citations. Previous affiliations of Saibal Mukhopadhyay include IBM & Purdue University.

Papers
More filters
Journal ArticleDOI

A 190 nA Bias Current 10 mV Input Multistage Boost Regulator With Intermediate-Node Control to Supply RF Blocks in Self-Powered Wireless Sensors

TL;DR: In this paper, a multistage boost regulator capable of generating 3V to supply RF blocks in self-powered wireless sensors from 10mV input voltage is presented, where bias power consumption is minimized using automated bias gating.
Proceedings ArticleDOI

Slew-aware clock tree design for reliable subthreshold circuits

TL;DR: A systematic approach to design the clock tree for subthreshold circuits to reduce the clock slew variations while minimizing the power dissipation in the tree is proposed and a dynamic nodal capacitance control technique is proposed that allows larger slew at the earlier nets of the tree while controlling it more aggressively near the sink nodes.
Journal ArticleDOI

Negative Gate Transconductance in Gate/Source Overlapped Heterojunction Tunnel FET and Application to Single Transistor Phase Encoder

TL;DR: In this paper, negative gate transconductance (NGT) is shown in gate/source overlapped heterojunction tunnel FET (SO-HTFET), where depletion region in the gate overlapped source region reduces the electric field along channel resulting in reduced band-to-bandtunneling and NGT.
Journal ArticleDOI

Multispectral Information Fusion With Reinforcement Learning for Object Tracking in IoT Edge Devices

TL;DR: This work uses task-driven feedback as a reward signal for their reinforcement learning-based multispectral input fusion, which not only improves tracking accuracy but also maximizes modality-specific information as intended by the user.
Journal ArticleDOI

Design and Analysis of a Neural Network Inference Engine Based on Adaptive Weight Compression

TL;DR: This paper presents design of an energy-efficient neural network inference engine based on adaptive weight compression using a JPEG image encoding algorithm to maximize compression ratio with minimum accuracy loss.