Spiking Neural Network For Energy Efficient Learning And Recognition
Nowadays, people are confronted with an increasingly large amount of data and a tremendous change of human-machine interaction modes. It is a challenging and time-consuming task for traditional computing system to deal with the content of information. The use of applications consumes energy and hard...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
International Journal of Scientific and Technology Research
2020
|
| Online Access: | http://eprints.utem.edu.my/id/eprint/25729/2/SPIKING-NEURAL-NETWORK-FOR-ENERGY-EFFICIENT-LEARNING-AND-RECOGNITION.PDF http://eprints.utem.edu.my/id/eprint/25729/ https://www.ijstr.org/final-print/nov2020/Spiking-Neural-Network-For-Energy-Efficient-Learning-And-Recognition.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Nowadays, people are confronted with an increasingly large amount of data and a tremendous change of human-machine interaction modes. It is a challenging and time-consuming task for traditional computing system to deal with the content of information. The use of applications consumes energy and hard to perform through standard programmed algorithms. Spiking neural networks have emerged that achieve favourable advantages in terms of energy and time efficiency by using spikes for computation and communication as well as solving different problems such as pattern classification and image processing. Therefore, an energy-efficient spiking feedforward computing system is presented to evaluate its performance. Common building blocks and techniques used to implement a spiking neural network are investigated to identify design parameters for hardware-based neuron implementations. Izhikevich neuron, Address-Event Representation system and Spiking-Timing-Dependent Plasticity module are developed by
using Vivado software. Demonstration of digit recognition using SNN hardware implementation on FPGA has been performed. The energy consumption of the system is only 136mW and low hardware resource utilization has been observed. This work presents essential properties of a spiking feedforward computing system that emulates the behaviour of biological neural networks, showing the potential for learning and classification in significantly reduced energy resources |
|---|