Mark Ogbodo の履歴(No.11)

Members-Internal

Fault-tolerant Spiking Neuromorphic System based on Light-weight On-chip Learning Algorithm

Research Background†

TBA

Research Goal†

The goal of this Doctoral thesis is to research and implement a Deep Spiking Neural Network Architecture with on-chip learning scheme and based on the previously developed schemes NASH1

The expected outputs from this research are:

(1) An efficient adaptive configuration method which enables reconfiguration of different SNN parameters (spike weights, routing, hidden layers, topology, etc.)
(2) An Efficient Multicast Fault-tolerant Routing Algorithm for the neurochip
(3) Efficient on-chip learning Algorithm
(4) To demonstrate the performance of the algorithms and the system, an FPGA implementation shall be developed and evalauted with several biological SNNs. In addition, a VLSI implementation shall be also developed.

TBA.

↑

Research schedule†

↑

Step 1: SNN LEARING ALGORITHMS AND IMPLEMENTATION SURVEY†

↑

April 25, 2019, 17:00†

Reading 1: Analytic Performance Assessment and High-throughput Low-latency Spike Routing Algorithm and Architecture for Spiking Neural Network Systems, Jnl Supercomputing, 2019.
- Summarize the paper and make a presentation
  - Paper Summary (5/6/2019, Time:7:10 PM) 562019_Reading1_Slides.pptx

↑

May 13, 2019, 17:00†

Reading 2: Simplified spiking neural network architecture and STDP learning algorithm applied to image classification, EURASIP Journal on Image and Video Processing, 2015
- Summarize the paper and make a presentation
  - Paper Summary (5/17/2019, Time:11:47 AM) 5141_Reading2_Slides.pptx;

Conclude Reading 2, SNN Learnign Algorithms and Hardware Implementation Survey
- Finalyse the Readig 2, Report about NN Learning Survey (May 29, 2019, 11:00 AM)
  - Reading 2 Conclusion (5/29/2019, Time:01:25 PM) Reading_2_Slides.pptx;
  - Report on SNN Learning Survey (5/29/2019, Time:01:25 PM) SNN_Learning_Algorithm_Survey_Draft.pdf;

↑