Rivu Midya

Professional experience

Dr. Rivu Midya is an Assistant Professor in the Mike Wiegers Department of Electrical and Computer Engineering at Kansas State University. He received his Ph.D. in Electrical and Computer Engineering from the University of Massachusetts Amherst in 2022. Prior to this he also received his MS degree in Electrical and Computer Engineering from the University of Massachusetts Amherst in 2017. He received his B Tech Degree in 2014 from West Bengal University of Technology.

Dr. Midya’s research lies at the intersection of emerging electronic devices, neuromorphic computing, and hardware-enabled artificial intelligence. His work focuses on memristive devices and arrays, in-memory computing, bio-inspired learning, and energy-efficient hardware architectures for intelligent sensing and computation. He is particularly interested in developing device–algorithm co-designed systems in which emerging memory devices directly implement learning and inference operations.

His research has contributed to a portfolio of peer-reviewed publications in leading journals and conferences and has benefited from projects supported by the Air Force Office of Scientific Research and the National Science Foundation. Through collaborations spanning materials, devices, circuits, algorithms, and system-level applications, Dr. Midya seeks to translate advances in emerging hardware into practical computing platforms that offer improved energy efficiency, adaptability, and resilience.

Research

Dr. Rivu Midya’s research lies at the intersection of memristive devices, neuromorphic computing, and energy-efficient artificial intelligence. His work connects device physics, computing architectures, and learning algorithms to develop hardware for intelligent information processing. Current and emerging research directions include:

• Memristive devices and in-memory computing: Developing nanoscale memory and switching devices for neural computation; investigating how material properties, device dynamics, and array architectures can support energy-efficient information processing.
• Learning algorithms and hardware–algorithm co-design: Developing efficient neural-network training methods and hardware-aware optimization strategies; examining how numerical precision, device variability, and computational constraints influence learning, convergence, and inference performance.

• Flexible electronics and neuromorphic sensor fusion: Exploring the integration of flexible sensors with memristive devices and neuromorphic circuits to combine information from multiple sensing modalities; developing approaches for low-power, adaptive sensory processing in wearable systems, electronic skin, and intelligent human–machine interfaces.
• Biomimetic and neuromorphic computing: Developing synaptic and neuronal circuits that emulate biological functions such as plasticity, signal integration, and adaptive firing; investigating how memristive device dynamics and circuit architectures can support learning, memory, and energy-efficient neural information processing.

Academic highlights