Practical Implementation
Practical implementation in scientific research focuses on translating theoretical concepts and algorithms into functional systems and applications. Current research emphasizes efficient model compression techniques (e.g., knowledge distillation, quantization) for resource-constrained environments like FPGAs, as well as robust and accurate implementations of established algorithms (e.g., gradient descent, PCA) for various applications, including biomedical image analysis and robotics. This work is crucial for bridging the gap between theoretical advancements and real-world impact, enabling the deployment of AI and other advanced technologies in diverse fields.
Papers
Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging
Ismail Erbas, Vikas Pandey, Aporva Amarnath, Naigang Wang, Karthik Swaminathan, Stefan T. Radev, Xavier Intes
A five-bar mechanism to assist finger flexion-extension movement: system implementation
Araceli Zapatero-Gutiérrez, Eduardo Castillo-Castañeda, Med Amine Laribi (COBRA)
LTNtorch: PyTorch Implementation of Logic Tensor Networks
Tommaso Carraro, Luciano Serafini, Fabio Aiolli
Development of Bidirectional Series Elastic Actuator with Torsion Coil Spring and Implementation to the Legged Robot
Yuta Koda, Hiroshi Osawa, Norio Nagatsuka, Shinichi Kariya, Taeko Inagawa, Kensaku Ishizuka