Chiara Bartolozzi is Researcher at the Italian Institute of Technology. She earned a degree in Engineering at University of Genova (Italy) and a Ph.D. in Neuroinformatics at ETH Zurich, developing analog subthreshold circuits for emulating biophysical neuronal properties onto silicon and modelling selective attention on hierarchical multi-chip systems. She is currently leading the Event-Driven Perception for Robotics group, with the aim of applying the “neuromorphic” engineering approach to the design of robotic platforms as enabling technology towards the design of autonomous machines. Chiara has participated to a number of EU funded projects, she is currently coordinating the European Training Network “NeuTouch”, where 15 PhD students are studying how touch perception works in humans and animals, in order to develop artificial touch perception systems for robots and hand prosthesis. As leader of the educational activities of the coordination and support action NEUROTECH, she is co-organising the Neuromorphic Colloquium, a series of online events to build up educational material for the next generation of neuromorphic researchers. She is an IEEE member, actively supporting the CAS and RAS societies. In 2020, she has co-chaired “AICAS2020”, on Circuits and systems for efficient embedded AI.
Since the first prototypes of neuromorphic vision sensors and computing devices, part of the community focused its efforts in deploying neuromorphic devices in practical applications, to exploit their intrinsic compression, low latency, high temporal resolution, high dynamic range. The quest to find the best strategy to exploit neuromorphic engineering is still open, but a lot of progress has been made. In this talk, I’ll describe possible approaches towards the development of neuromorphic perception for robots and discuss the relevance of the development of neuromorphic sensing for touch and other modalities.
Prof. Ivan K. Schuller, the director of the Center for Advanced Nanoscience (CAN) at the University of California-San Diego, is a Solid State Physicist. He is winner of major awards such as the Lawrence Award-US Department of Energy, the Vannevar Bush fellowship-Department of Defense and several awards from the American Physical Society, the Materials Research Society and the International Union of Materials Research Societies. Prof. Schuller received his Licenciado from the University of Chile, PhD from Northwestern University and an Honoris Causa Doctorate from the Spanish Universidad Complutense the largest European University. He is a member of the Latin American, Chilean, Spanish, Belgian and Colombian Academies of Science. His more than 650 papers and 20 patents have been dedicated to many aspects of solid state and materials physics in Nano and Meso science with possible applications to Neuromorphic Computing and Sensors. His extensive artistic activities have spanned the award winning production and writing of plays, movies, YouTube videos and acting in a variety of venues. He was recently elected a fellow of the American Academy of Arts and Sciences.
Data manipulation (memory, computation, communications, data mining, sensing) in its many forms drives our modern civilization. The continuous increase in hardware packing density and phenomenal decrease in cost (Moore’s law) has been key to the development of the information revolution. This was fueled by the discovery of revolutionary scientific concepts such as quantum mechanics, coupled with the development of novel materials and solid-state devices. It is however agreed that the enhanced computational capabilities will soon (within the next 5-10 years ?) slow down considerably due to a variety of issues which are connected probably to the foundation of the classical Turing-von Neumann paradigm for computing. Because of this the IEEE launched the Rebooting Computing initiative to rethink computing from all its aspects including materials, devices, systems and software.
To implement this, new hardware concepts, based on transformative scientific concepts, are needed. This includes reevaluation of data manipulation concepts for software and systems. By necessity this will require development of energy efficient hardware including novel device concepts and quantum materials with unusual functional properties. The coupling of spin, charge and structural degrees of freedom, present in quantum materials, lead to unique functional properties and opportunities for the invention of functional devices which may impact the development of new energy efficient neuromorphic systems.
The work was supported as part of the Quantum Materials for Energy Efficient Neuromorphic Computing (Q-MEEN-C), an Energy Frontier Research Center funded by the U.S. Department of Energy, Office of Science. The development of new functional quantum materials was partially funded by the Air Force Office of Scientific Research.