Praveen Eppa
Papers
1
Total Citations
6
H-Index
1
About
Praveen Eppa is a researcher whose work focuses on the efficient deployment of deep learning models, particularly Convolutional Neural Networks (CNNs), on resource-constrained embedded devices. His key research areas include model quantization, inference optimization, and the practical application of AI in fields like automotive, industrial, and medical imaging. Eppa’s major contribution is the development of dynamic and predictive quantization techniques for CNN inference, a method that significantly reduces computational and memory demands without sacrificing accuracy. This work, detailed in his highly cited 2018 paper, addresses a critical bottleneck in bringing powerful AI to edge devices. With over 6 citations, his research has provided a foundational approach for engineers and scientists seeking to balance performance with efficiency in real-world systems. Eppa’s achievements highlight his role in bridging the gap between advanced deep learning theory and practical, deployable solutions, making him a notable figure in the embedded AI community.
Research Focus
Key Achievements
Top Papers
- 1CNN Inference: Dynamic and Predictive Quantization6 citations · 2018