Dang, Nam Khanh and Abdallah, Abderazek Ben (2019) An Efficient Software-Hardware Design Framework for Spiking Neural Network Systems. In: The International Conference on Internet of Things, Embedded Systems and Communications (IINTEC 2019). (In Press)
This is the latest version of this item.
|
PDF
- Accepted Version
Download (915kB) | Preview |
Abstract
Spiking Neural Network (SNN) is the third generation of Neural Network (NN) mimicking the natural behavior of the brain. By processing based on binary input/output, SNNs offer lower complexity, higher density and lower power consumption. This work presents an efficient software-hardware design framework for developing SNN systems in hardware. In addition, a design of low-cost neurosynaptic core is presented based on packet-switching communication approach. The evaluation results show that the ANN to SNN conversion method with the size 784:1200:1200:10 performs 99% accuracy for MNIST while the unsupervised STDP archives 89% with the size 784:400 with recurrent connections. The design of 256-neurons and 65k synapses is also implemented in ASIC 45nm technology with an area cost of 0.205 mm2.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Electronics and Communications |
| Divisions: | Key Laboratory for Smart Integrated Systems (SISLAB) |
| Depositing User: | Khanh N. Dang |
| Date Deposited: | 04 Jan 2020 05:42 |
| Last Modified: | 04 Jan 2020 05:42 |
| URI: | http://eprints.uet.vnu.edu.vn/eprints/id/eprint/3916 |
Available Versions of this Item
-
An Efficient Software-Hardware Design Framework for Spiking Neural Network Systems. (deposited 06 Dec 2019 07:51)
- An Efficient Software-Hardware Design Framework for Spiking Neural Network Systems. (deposited 04 Jan 2020 05:42) [Currently Displayed]
Actions (login required)
 |
View Item |
