Speakers

Professor at Purdue University, USA

https://engineering.purdue.edu/NRL/Group

Title: Re-thinking Edge Computing with Neuro-Inspired Learning: Sensors, Algorithms, and Hardware Architecture

Abstract: Advances in machine learning, notably deep learning, have led computers to match or surpass human performance in several cognitive tasks including vision, speech and natural language processing. However, implementation of neural algorithms in conventional "von-Neumann" architectures are several orders of magnitude more area and power expensive than the biological brain. Hence, we need fundamentally new approaches to sustain the exponential growth in performance at high energy-efficiency. Exploring the new paradigm of computing necessitates a multi-disciplinary approach: exploration of new learning algorithms inspired from neuroscientific principles, developing network architectures best suited for such algorithms, new hardware techniques to achieve orders of improvement in energy consumption, and nanoscale devices that can closely mimic the neuronal and synaptic operations. In this talk, I will first present our recent work on hybrid learning algorithms (using both standard deep learning combined with spike-based computing units) to achieve high energy efficiency and higher accuracy compared to standard deep-learning techniques. In particular, we focused on autonomous vision-based navigation as an application driver and developed efficient and low-complexity hybrid learning algorithms for optical flow, segmentation, object detection, tracking, and avoidance, gesture recognition with both frame based and DVS cameras as input sensors. The above algorithms for edge applications require fast and energy-efficient processing, beyond the capabilities of today’s von-Neumann based commercial hardware. In the second part of the talk I will present our work on in-memory computing-based machine learning hardware that has the potential to achieve orders of magnitude improvement in energy compared to today’s deep learning hardware.

Short bio: Kaushik Roy is the Edward G. Tiedemann, Jr., Distinguished Professor of Electrical and Computer Engineering at Purdue University. He received his BTech from Indian Institute of Technology, Kharagpur, PhD from University of Illinois at Urbana-Champaign in 1990, and joined the Semiconductor Process and Design Center of Texas Instruments, Dallas, where he worked for three years on FPGA architecture development and low-power circuit design. His current research focuses on cognitive algorithms, circuits and architecture for energy-efficient neuromorphic computing/ machine learning, and neuro-mimetic devices. Kaushik has supervised more than 100 PhD dissertations and his students are well placed in universities and industry. He is the co-author of two books on Low Power CMOS VLSI Design (John Wiley & McGraw Hill). 

Title:

Abstract:

Short bio: Melika Payvand is a senior research scientist (starting as an assistant professor in Feb 2023) at the Institute of Neuroinformatics, University of Zurich and ETH Zurich. She received her M.S. and Ph.D. in electrical and computer engineering from the University of California Santa Barbara in 2012 and 2016 respectively. Her research interest is understanding the organizing principles of biological nervous systems and employing them to build more efficient and intelligent artificial systems, following a co-design approach across devices, circuits, and algorithms.

She is an active member of the neuromorphic community, co-coordinating the European NEUROTECH project, co-chairing the International Conference on Neuromorphic Systems (ICONS), and serving as a scientific committee member of the Capocaccia neuromorphic intelligence workshop.

She has served as the chair of the neuromorphic engineering track at the IEEE ISCAS conference. She has co-organized the Women in Circuits and Systems (WiCAS) event at the IEEE ICECS conference. She has also served as the guest editor of Frontiers in Neuroscience and the IOP journal of neuromorphic computing and engineering. She is the winner of the best neuromorph award of the 2019 Telluride neuromorphic workshop. 

Professor at TU Berlin, Germany

https://sites.google.com/view/guillermogallego/home

Title: Event-based motion estimation with one or more cameras

Abstract: Event cameras are novel vision sensors that mimic functions from the human retina and offer potential advantages over traditional cameras to tackle challenging problems in robotics, such as those involving high-speed motion, high dynamic range illumination and power-constrained scenarios. This talk discusses the fundamental question of how the data (called events) can be processed to solve a target task. In particular, I will present recent advances from the Robotic Interactive Perception Lab at TU Berlin on processing event data in topics of interest (ego-motion estimation (SLAM), optical flow estimation, 3D reconstruction, animal monitoring, etc.).

Short bio: Prof. Gallego leads the Robotic Interactive Perception Laboratory at TU Berlin and at the Einstein Center Digital Future.
He is also a Principal Investigator at the Science of Intelligence Excellence Cluster and co-director of the HEIBRiDS research school, Berlin, Germany.
He received the PhD degree in Electrical and Computer Engineering from Georgia Tech in 2011, supported by a Fulbright Scholarship.

Title:

Abstract:

Short bio: Dr. Guido de Croon is a Full Professor at Delft University of Technology Netherlands.  Dr. Croon’s research interests focus on bio-inspired robotics, micro air vehicles, vision-based navigation, and swarm robotics.

He also holds the position of Principal Investigator at Micro Air Vehicle Lab, (MAVLab) TUDelft.

He obtained his PhD in Artificial Intelligence (AI) at Maastricht University. He has also worked for the European Space Agency for several years.

Assistant Professor at Yale University, USA

https://seas.yale.edu/faculty-research/faculty-directory/priya-panda

Title: Advancing Robotic Perception through Spiking Neural Networks

Abstract: Spiking Neural Networks (SNNs) represent a paradigm shift in artificial intelligence, offering a bio-inspired approach that closely mimics the human brain's information processing mechanisms. This presentation will explore the potential of SNNs in the context of embodied neuromorphic AI for robotic perception. We will delve into the fundamental principles of SNNs, highlighting their energy efficiency and biological plausibility. The talk will emphasize how these characteristics make SNNs particularly well-suited for robotic applications, where real-time processing, adaptability, and power constraints are critical factors. We will discuss specific use cases in robotic perception, such as visual and auditory processing. Additionally, we will address the current challenges in implementing SNNs for robotic systems, including algorithm optimization, hardware integration, and the development of suitable learning paradigms. By examining the intersection of SNNs, neuromorphic hardware, and robotics, this presentation aims to stimulate discussion on the future of brain-inspired computing in autonomous systems and its potential for robotic perception.

Short bio: Priya Panda is an assistant professor in the electrical engineering department at Yale University, USA. She received her B.E. and Master's degree from BITS, Pilani, India in 2013 and her Ph.D. from Purdue University, USA in 2019. During her PhD, she interned in Intel Labs where she developed large scale spiking neural network algorithms for benchmarking the Loihi chip. She is the recipient of the 2019 Amazon Research Award, 2022 Google Research Scholar Award, 2022 DARPA Riser Award, 2023 NSF CAREER Award, 2023 DARPA Young Faculty Award. She has also received the 2022 ISLPED Best Paper Award and 2022 IEEE Brain Community Best Paper Award. Her research interests lie in Spiking Neural Networks, and Efficient Hardware Accelerators.

Assistant Professor at Delft University of Technology, The Netherlands

https://chfrenkel.github.io/

Title: Merging insights from artificial and biological neural networks for neuromorphic edge intelligence

Abstract: The development of efficient bio-inspired training algorithms and adaptive hardware is currently missing a clear framework. Should we start from the brain computational primitives and figure out how to apply them to real-world problems (bottom-up approach), or should we build on working AI solutions and fine-tune them to increase their biological plausibility (top-down approach)? In this talk, we will see why biological plausibility and hardware efficiency are often two sides of the same coin, and how neuroscience- and AI-driven insights can cross-feed each other toward low-cost on-device training.

Short bio: Charlotte Frenkel is an Assistant Professor at Delft University of Technology, The Netherlands. She received her Ph.D. from Université catholique de Louvain in 2020 and was a post-doctoral researcher at the Institute of Neuroinformatics, UZH, and ETH Zürich, Switzerland. Her research aims at bridging the bottom-up (bio-inspired) and top-down (engineering-driven) design approaches toward neuromorphic intelligence, with a focus on digital neuromorphic processor design, embedded machine learning, and brain-inspired on-device learning.
Dr. Frenkel received a best paper award at the IEEE International Symposium on Circuits and Systems (ISCAS) 2020 conference, and her Ph.D. thesis was awarded the FNRS / Nokia Bell Scientific Award 2021 and the FNRS / IBM Innovation Award 2021. In 2023, she was awarded prestigious AiNed Fellowship and Veni grants from the Dutch Research Council (NWO). She served as a program co-chair of the NICE conference and of the tinyML Research Symposium, as a TPC member of IEEE ESSERC, and as an associate editor for the IEEE Transactions on Biomedical Circuits and Systems.

Founder & CEO & CTO at Unitree Robotics, China

https://www.unitree.com/en/

Title: The importance of physical robots for realizing embodied AI

Abstract: Present some of Unitree's robots, current hardware and software developments. Sharing thoughts for the future development of robots with embodied AI.

Short bio: Wang Xingxing, founder/CEO/CTO of Unitree Robotics. During his master's degree (2013~2016), he independently developed a low-cost high performance quadruped robot XDog. After graduated he joined DJI(May 2016) and found Unitree Robotics(August 2016), leading the company to become a global leader in the commercialization of quadruped robots and humanoid robots. Up to now, he have been applied 150+ patents.