Parallel simulation of spiking neural networks
Spiking neural networks transfer information through activation spikes that carry information through their weight and temporal delay. The behavior of a spiking neural network can be simulated through discrete event simulation, where neurons are framed as discrete logical processes. However, due to...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/153506 |
| _version_ | 1811681251747168256 |
|---|---|
| author | Tang, Marcus Zi Yang |
| author2 | Huang Shell Ying |
| author_facet | Huang Shell Ying Tang, Marcus Zi Yang |
| author_sort | Tang, Marcus Zi Yang |
| collection | NTU |
| description | Spiking neural networks transfer information through activation spikes that carry information through their weight and temporal delay. The behavior of a spiking neural network can be simulated through discrete event simulation, where neurons are framed as discrete logical processes. However, due to the large size of the network and the number of update events occurring, sequential discrete event simulation is unable to simulate a large population of spiking neurons effectively.
Application of parallel discrete event simulation techniques to simulate spiking neural networks allows training using biologically plausible learning rules on a large-scale platform that can be potentially decentralized. In this report, a prototype for GPU-based discrete-event simulation of spiking neurons is explored, demonstrating convergence and unsupervised learning using GPU-based algorithms. |
| first_indexed | 2024-10-01T03:37:59Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/153506 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:37:59Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1535062021-12-06T07:26:15Z Parallel simulation of spiking neural networks Tang, Marcus Zi Yang Huang Shell Ying School of Computer Science and Engineering ASSYHUANG@ntu.edu.sg Engineering::Computer science and engineering Spiking neural networks transfer information through activation spikes that carry information through their weight and temporal delay. The behavior of a spiking neural network can be simulated through discrete event simulation, where neurons are framed as discrete logical processes. However, due to the large size of the network and the number of update events occurring, sequential discrete event simulation is unable to simulate a large population of spiking neurons effectively. Application of parallel discrete event simulation techniques to simulate spiking neural networks allows training using biologically plausible learning rules on a large-scale platform that can be potentially decentralized. In this report, a prototype for GPU-based discrete-event simulation of spiking neurons is explored, demonstrating convergence and unsupervised learning using GPU-based algorithms. Bachelor of Engineering (Computer Science) 2021-12-06T07:26:15Z 2021-12-06T07:26:15Z 2021 Final Year Project (FYP) Tang, M. Z. Y. (2021). Parallel simulation of spiking neural networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153506 https://hdl.handle.net/10356/153506 en SCSE20-0931 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Tang, Marcus Zi Yang Parallel simulation of spiking neural networks |
| title | Parallel simulation of spiking neural networks |
| title_full | Parallel simulation of spiking neural networks |
| title_fullStr | Parallel simulation of spiking neural networks |
| title_full_unstemmed | Parallel simulation of spiking neural networks |
| title_short | Parallel simulation of spiking neural networks |
| title_sort | parallel simulation of spiking neural networks |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/153506 |
| work_keys_str_mv | AT tangmarcusziyang parallelsimulationofspikingneuralnetworks |