Teresa Riesgo
Papers
2
Total Citations
40
H-Index
2
About
Teresa Riesgo is a leading figure in reconfigurable hardware and embedded neural systems, with her work bridging the gap between adaptive algorithms and efficient digital architectures. Her research centers on FPGA-based implementations of neural networks for real-time image recognition, a critical area for robotics, security, and autonomous systems. Riesgo’s major contribution lies in the design of specialized Tiny Neural Networks (TNNs) that combine online training capability with hardware reconfigurability. Her most cited work (31 citations) introduces a reconfigurable hardware architecture for shape recognition using these TNNs, emphasizing expandability through modular basic units. A related study (9 citations) further demonstrates an FPGA implementation that leverages on-line reconfiguration, enabling the system to adapt its structure without halting operation—a key advantage for embedded applications. By proving that compact, trainable neural networks can be efficiently mapped onto reconfigurable logic, Riesgo has advanced the practicality of intelligent, low-power hardware. Her achievements highlight a pioneering approach to merging machine learning with digital design, offering a scalable pathway for deploying adaptive vision systems in resource-constrained environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2