Enrico Ferrari
Papers
1
Total Citations
2
H-Index
1
About
Enrico Ferrari is a researcher at the forefront of making machine learning practical for real-world, resource-constrained systems. His primary research areas include automated machine learning (AutoML), edge computing, and efficient data pre-processing and post-processing pipelines. Ferrari’s most notable contribution is the development of the VAMPIRE framework—a vectorized, automated ML solution designed specifically for edge applications. This work addresses a critical challenge: deploying sophisticated ML models on devices with limited computational power, such as IoT sensors and mobile platforms. By streamlining the entire ML workflow from data preparation to final prediction, VAMPIRE enables faster, more efficient model deployment without sacrificing accuracy. While his most-cited paper has garnered 2 citations to date, its impact lies in its practical utility for engineers and researchers working on embedded AI. Ferrari’s work stands out for its focus on bridging the gap between high-performance ML algorithms and the hardware constraints of edge devices, making him a key contributor to the growing field of tinyML and democratized artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1