France-Stanford Center - Undergraduate Internship Neuromorphic Computing
Sponsored by
Stanford Global Studies
France-Stanford Center for Interdisciplinary Studies
Funding:
See maximum funding amount and funding details below
Open To:
Freshman
Sophomore
Junior
Senior
Summer
Applications closed
Applications closed on February 26, 2020
Approximate Offer Date:
Sunday, March 15, 2020
LIRMM – Laboratory of Informatics, Robotics, and Microelectronics of Montpellier is a 350-person cross-faculty research entity of the University of Montpellier and the CNRS. LIRMM research activities cover a broad range of topics, including: design and verification of integrated, mobile and communicating systems, modeling of complex systems, research on algorithms, bioinformatics, human-machine interaction, robotics, database, distributed systems, AI, knowledge engineering and more. Since 2008, LIRMM has been involved in more than 40 EU projects). LIRMM obtained A+ during the HCERES 2010 & 2014 evaluations. In addition, LIRMM has chosen health, agriculture and environmental sciences as priority domains of application for its research in Informatics and Robotics. In 2020, LIRMM and Stanford University will partner under the International Research Laboratory program from CNRS to facilitate staff and student exchanges as well as supporting existing and future scientific collaborations in the next 4 to 8 years. Existing collaborations cover different fields of research from computer science to robotics and have already accomplished great scientific outcomes in: (i) Underwater robotics, (ii) Medical robotics, (iii) Semantic Web.
Eligibility and Requirements:
Neuro-inspired computing employs technologies that enable brain-inspired computing hardware for more efficient and adaptive intelligent systems. Mimicking the human brain and nervous system, these computing architectures are excellent candidates for solving complex and large-scale associative learning problems. In this internship, we will investigate and design oscillatory neural networks (ONN) for implementing neuromorphic computing. We will compare it to more conventional Spiking Neural Networks (SNN) or non-spiking Artificial Neural Networks (ANN) for performance and energy efficiency.