【國際學術講座】

時間：111年12月7日(星期三) 下午4：00-6：00

地點：國立清華大學/台達館209室

對象：大專院校師生

備有點心、晚餐，歡迎踴躍參加

1. Title: "Merging insights from artificial and biological neural networks for neuromorphic edge intelligence"
2. Abstract:
   
   While taking inspiration from biological neural networks outlines order-of-magnitude efficiency improvements over current artificial-neural-network accelerators, the road toward demonstrating a competitive advantage with bio-inspired neuromorphic processing devices is still unclear.
   In this talk, I'll first cover the main trends in the field of neuromorphic engineering, the bottom-up and top-down design strategies, as well as key concepts linked to spike-based computation and learning algorithms.
   I'll then highlight how these elements integrate into our latest chip ReckOn (ISSCC'22), a 0.45-mm² spiking recurrent neural network processor enabling end-to-end task-agnostic online learning over second-long timescales. Benchmarked on vision, audition and navigation tasks within a learning power budget of 50µW at 0.5V, ReckOn illustrates how a neuromorphic approach can bring unique advantages for edge devices that continuously adapt to their environment.
3. Short bio:
   
   Charlotte Frenkel received the M.Sc. degree (summa cum laude) in Electromechanical Engineering and the Ph.D. degree in Engineering Science from Université catholique de Louvain (UCLouvain), Louvain-la-Neuve, Belgium in 2015 and 2020, respectively. In February 2020, she joined the Institute of Neuroinformatics, UZH and ETH Zürich, Switzerland, as a postdoctoral researcher. Since July 2022, she is an Assistant Professor at Delft University of Technology, The Netherlands.
   Her current research aims at bridging the bottom-up and top-down design approaches toward neuromorphic edge intelligence, with a focus on spiking neural network processor design, embedded machine learning, and on-chip training algorithms.
   Ms. Frenkel received a best paper award at the IEEE ISCAS 2020 conference and the FNRS Nokia Bell Labs Scientific Award 2021, the FNRS IBM Innovation Award 2021 and the UCLouvain/ICTEAM Best Thesis Award 2021 for her Ph.D. thesis. She serves as a TPC member for the tinyML Research Symposium, tinyML EMEA, IEEE ESSCIRC, IEEE ISLPED, and IEEE DATE since 2022, as a member of the neuromorphic systems and architecture technical committee of the IEEE CAS society since 2021, and as a reviewer for various conferences and journals, including the IEEE J. of Solid-State Circuits, IEEE Trans. on Neural Networks and Learning Syst., IEEE Trans. on Circuits and Syst. I/II, IEEE Trans. on Biomed. Circuits and Syst., Nature, Nature Electronics, and Nature Machine Intelligence. She presented several invited talks, including two keynotes at the tinyML EMEA technical forum 2021 and at the Neuro-Inspired Computational Elements (NICE) neuromorphic conference 2021. She is the chair of the tinyML initiative on neuromorphic engineering, is a program co-chair of the NICE conference 2023, and serves as an associate editor for the IEEE Transactions on Biomedical Circuits and Systems journal.