Amogh Agrawal

Papers

Total Citations

H-Index

About

Amogh Agrawal is a leading researcher in the field of in-memory computing (IMC) and hardware accelerators for machine learning, with a particular focus on deep neural networks (DNNs). His most cited work, "Circuits and Architectures for In-Memory Computing-Based Machine Learning Accelerators" (2020, 41 citations), addresses the critical challenge of efficiently implementing increasingly complex DNN models—used in computer vision, speech recognition, and robotics—by moving beyond traditional von Neumann architectures. Agrawal’s key contributions lie in designing novel circuits and architectures that perform matrix-vector multiplications directly within memory arrays, dramatically reducing data movement and energy consumption. This work has been foundational for advancing energy-efficient AI hardware, enabling real-time inference on edge devices. His research bridges the gap between circuit-level innovation and system-level performance, making him a prominent voice in the push toward next-generation accelerators. With a growing citation impact, Agrawal’s insights continue to shape how researchers and engineers approach the hardware bottlenecks of modern machine learning, solidifying his reputation as a key contributor to the future of intelligent, low-power computing.