Events

Home  >  Events  >  Seminars  >  Content

Financial Academic Lecture 21--Towards Next-Generation Auditory Information Processing : A Neuromorphic Approach

2024-04-09 09:48:11

Topic:

Towards Next-Generation Auditory Information Processing:A Neuromorphic Approach

Lecturer:

Dr.JibinWu is an Assistant Professor in the Department ofComputing,The Hong Kong Polytechnic University.His research interests include brain - inspired artificial intelligence neuromorphic computing,computational audition,speechprocessing,and machine learning.His primary dedication lies in unraveling the computational principles and architectures of biological brains while also striving to develop cutting-edge brain-inspired cognitive machines that possess exceptional intelligence energy efficiency,robustness,adaptability,and explainability.Dr.Wuhas actively published in prestigious conferences and journals in artificial intelligence and speech processing,including NeurlPSICLR,AAAI,TPAMI,TNNLS,TCDS.TASLP.and Neurocomputing.He currently serves as the Associate Eitorsfor IEEE Transactions on Neural Networks and Learning Systems and IEEE Transactions on Cognitive and Developmental Systems.

Abstract:

Hearing is a vivid part of our conscious lives.Driven by recent advances in artificial intelligence (Al),the capability of machine hearing systems has improved by leaps and bounds over the lastdecade.Throughoutthe history of machine hearing research neuroscience has played a pivotal role by offering a bountiful source of inspiration for novel acoustic features,algorithms,and computational models.

In thistalk,I will present our recent research outcomes on neuromorphic auditory information processing that is groundedothe brain-inspired spiking neural networks (SNNs).In particular,Iwill present the technology breakthroughs in:1) auditory neural codes that can efficiently and effectively encode sound signals;2)learning algorithms that supportrapid and efficient pattern recognition using SNNs;3)task-specific neural architectures that grounded on the pre-existing neural structures;I will conclude the talk by sharing my long-term vision of developing low-power,reliable,adaptive,andexplainable neuromorphic cognitivemachines.

Time: March 31,202410:00-12:00

Venue: B609,YiFuXinxiBuilding,Central Campus