Janardhan Rao Doppa
Papers
5
Total Citations
58
H-Index
3
About
Janardhan Rao Doppa is a computer scientist whose research sits at the intersection of machine learning, edge artificial intelligence, and hardware-software co-design. His work principally addresses one of the most pressing challenges in modern AI deployment: enabling deep neural networks to run efficiently on resource-constrained mobile and edge platforms without sacrificing unacceptable levels of accuracy. Doppa's most influential contribution, cited 31 times, introduced a novel framework for dynamically trading off energy consumption and inference accuracy at runtime using pretrained deep models — a breakthrough for applications in object detection, robotics, and smart health. Building on this, his 2021 co-design framework (12 citations) extended these principles into a generalizable architecture supporting edge applications ranging from self-driving vehicles to augmented reality. His 2020 PETNet work further demonstrated this philosophy applied to 3D object shape prediction on mobile hardware. Beyond edge AI, Doppa has contributed to language grounding for robotics and, more recently, AI-driven decision support for specialty crop agriculture through the AgAID National AI Research Institute. Collectively, his research reflects a sustained commitment to making powerful AI systems practical, efficient, and applicable across diverse real-world domains.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Towards Problem Solving Agents that Communicate and Learn9 citations · 2017
- 4AgAID Institute—AI for agricultural labor and decision support3 citations · 2024
- 5