Scalable Homeostatic Neuro-inspired System

Research Background

Spiking neural networks (SNNs) are artificial neural network models that more closely mimic biological neural networks. In addition to neuronal and synaptic state, SNNs incorporate the variant time scale into their computational model. Since each neuron in these networks is connected to thousands of others, high bandwidth is required. Moreover, since the spike times are used to encode information in SNN, very low communication latency is also needed. The 2D-NoC was used as a solution to provide a scalable interconnection fabric in large-scale parallel SNN systems. The 3D-ICs have also attracted a lot of attention as a potential solution to resolve the interconnect bottleneck. The combination of these two emerging technologies provides a new horizon for IC designs to satisfy the high requirements of low power and small footprint in emerging AI applications...more

Research Goal

Research about an event-driven scalable neuromorphic system for edge computing.

Research Schedule

DateTask
☑️January 1st - March 31, 2020Running Demos and study of SW/HW tools
☑️April 1st - Jun 21, 2020SNN Learning Algorithms Survey
☑️Jun 22 - Oct 2, 2020Complete and submit paper of AEBIS
☑️Oct 3 - Nov 15, 2020Revise the AEBIS paper
Nov 16 - Dec 18, 2020Investigate the optimization of AEBIS and extend the work
Dec 19 - Jan 31, 2021Complete and submit paper of extended version of AEBIS
February 1 - February 24, 2021Understand K-means based Multicast Routing Algorithm and Architecture for 3D SNN NoC. Conduct a short survey about SNN mapping. See this opensource mapping sim https://github.com/drexel-DISCO/SpineMap and the author's paper
February 25 - March 31, 2021Propose an efficient (Possible target: low-latency, High-accuracy-->QoS) 3D QoS CMR (Clustering-Mapping-Routing) algorithm
April 1 - Mid of May, 2020Write and submit a paper of new 3D QoS CMR algorithm
Mid of May - June 6, 2021Evaluate with other biology (biomedical) applications
June 7 - July 11, 2021Write and submit a paper of AIRBiS system
July 12 - August 31, 2021Implement the new QoS CMR algorithm on hardware
September 1 - Mid of October, 2021Write and submit a paper of hardware version
Mid of October - November 31, 2021Study and propose a new fault-tolerant algorithm for multi-core 3D-NoC systems
December 1 - Mid of January, 2022Write and submit a paper for new fault-tolerant algorithm
Mid of January - February 28, 2022Implement an EV reservation prediction system using SNN (or CNN) on hardware implementation
March 1 - March 31, 2022Testing the system and prepare a paper
April 1 - April 30, 2022Investigate other bio-related topics and edge-computing system
May 1 - June 31, 2022Prepare and submit a paper
Schedule last Updated on: November/16/2020

Research Progress ===> previous tasks

Task 3

Achievements

Journal Papers

Conference Papers

My Shared Google Drive Folder

Site update


トップ   新規 一覧 検索 最終更新   ヘルプ   最終更新のRSS