[Seminar] “Functional Benefit of Plastic Spiking Neural Networks for Information Processing" by Dr. Huang

Dear all,

Neural Computation Unit (Doya Unit) would like to invite you to a seminar as follows.

Date: Monday, June 17, 2019
Time: 10:00 – 11:00
Venue: Meeting room C016, Lab1 Bldg.

Speaker: Dr. Xuhui Huang
                  Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences

Title:
Functional Benefit of Plastic Spiking Neural Networks for Information Processing
 
Abstract:
Spiking neural networks (SNNs) are considered as the third-generation neural network models, which exhibit the potential of energy efficiency due to the event-based computation. In this talk, I will report that how synaptic plasticity could benefit for information processing of SNNs, e.g., pattern recognition and sequence learning. Specifically, for pattern recognition, I will show that how spike-timing-dependent plasticity (STDP) could achieve the biologically plausible supervised learning as well as the fast unsupervised speech feature extraction; while for sequence learning, I will show how the short-term synaptic plasticity (STP) could serve as a self-organized mechanism for maintaining optimal information processing, in the face of long-term synaptic changes necessary for learning and memory. Those studies indicate that SNNs equipped with synaptic plasticity (STDP, STP, etc.) have the potential to effectively solve kinds of realistic information processing tasks in a neuroscience-inspired way.

We hope to see many of you at the seminar.

Sincerely,
Neural Computation Unit
Contact: ncus@oist.jp