The Swiss AI Lab IDSIA (Dalle Molle Institute for Artificial Intelligence)

of the University of Italian Switzerland (USI)

and the University of Applied Sciences and Arts of Southern Switzerland (SUPSI)

Using state-of-the-art machine learning, we focus on bridging the gap between the myoelectric data collected from patients within the INPUT project, and the desired control signal output for prostheses.

The IDSIA is a world-renowned non-profit research institute for artificial intelligence, located in Manno-Lugano in the southern part of Switzerland, and affiliated with both the university and the university of applied sciences of Lugano. It focuses on machine learning (deep neural networks, reinforcement learning), operations research, data mining, and robotics.



Research for INPUT involves the group of Prof. Jürgen Schmidhuber, best known for his work on self-improving general problem solvers, and Deep Learning using Neural Networks (NNs). Neural networks in their various forms (recurrent sequence learners, deep multi-stage processors for complex data) play a key role for processing the INPUT data, particular with respect to high long-term robustness in varying environmental conditions.

With its long-standing expertise in both foundational and applied machine learning, the IDSIA is optimally prepared for its role in the INPUT project, with the goal of delivering state-of-the-art myoelectric prosthesis control.

                                                               INPUT TEAM

Klaus Greff, MSc
PhD Candidate
Dr.-Ing. Michael Wand
Postdoctoral Researcher