Riccardo Berta
Papers
3
Total Citations
20
H-Index
3
About
Riccardo Berta is a leading researcher at the intersection of embedded systems and machine learning, specializing in deploying deep neural networks on severely resource-constrained devices. His work focuses on enabling intelligent edge computing, particularly through the optimization of neural networks for microcontrollers and embedded platforms. Berta’s major contributions include pioneering memory-efficient binary convolutional neural networks for microcontrollers, a breakthrough that allows complex AI tasks to run on devices with minimal computational resources. His 2022 paper on this topic has garnered 10 citations, highlighting its significance in the field. He has also advanced affordance detection for semi-autonomous systems, developing pipelines that operate within tight hardware constraints, and created tiny CNNs for embedded electronic skin systems, pushing the boundaries of tactile sensing in robotics. Berta’s research is instrumental in bridging the gap between high-performance AI and practical, low-power edge devices, making him a key figure in the evolution of tiny machine learning (TinyML) and its industrial applications.
Research Focus
Key Achievements
Top Papers
- 1Memory Efficient Binary Convolutional Neural Networks on Microcontrollers10 citations · 2022
- 2An Affordance Detection Pipeline for Resource-Constrained Devices5 citations · 2021
- 3A Tiny CNN for Embedded Electronic Skin Systems5 citations · 2022