Parth Mannan
Papers
2
Total Citations
25
H-Index
2
About
Parth Mannan is a researcher at the forefront of efficient and adaptive deep learning systems, with a primary focus on hardware-aware neural architecture search and lifelong learning. His most cited work, "GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware" (2018, 22 citations), introduces a novel framework that directly evolves neural network topologies on hardware, eliminating the need for hand-tuned architectures and massive labeled datasets. This approach enables continuous, on-device learning, addressing a critical bottleneck in deploying deep learning at the edge. By integrating evolutionary algorithms with hardware constraints, Mannan’s research paves the way for systems that can adapt in real-time without relying on cloud-based retraining. His contributions are particularly impactful for resource-constrained environments, such as IoT devices and autonomous systems, where efficiency and adaptability are paramount. With a growing citation footprint, Mannan’s work is shaping the future of lifelong machine learning, making deep learning more accessible and sustainable. His research stands out for its practical, hardware-centric approach, offering a compelling alternative to traditional, compute-intensive training paradigms.
Research Focus
Key Achievements
Top Papers
- 1
- 2