Event-driven continuous STDP learning with deep structure for visual pattern recognition

Liu, Daqi and Yue, Shigang (2018) Event-driven continuous STDP learning with deep structure for visual pattern recognition. IEEE Transactions on Cybernetics . ISSN 2168-2267

Documents
Event-driven Continuous STDP Learning with Deep Structure for Visual Pattern Recognition.pdf
[img]
[Download]
[img]
Preview
PDF
Event-driven Continuous STDP Learning with Deep Structure for Visual Pattern Recognition.pdf - Whole Document

1MB
Item Type:Article
Item Status:Live Archive

Abstract

Human beings can achieve reliable and fast visual pattern recognition with limited time and learning samples. Underlying this capability, ventral stream plays an important role in object representation and form recognition. Modeling the ventral steam may shed light on further understanding the visual brain in humans and building artificial vision systems for pattern recognition. The current methods to model the mechanism of ventral stream are far from exhibiting fast, continuous and event-driven learning like the human brain. To create a visual system similar to ventral stream in human with fast learning capability, in this study, we propose a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. Two novel continuous input mechanisms have been used to obtain the continuous input spiking pattern sequence. With the event-driven STDP learning rule, the proposed learning procedure will be activated if the neuron receive one pre- or post-synaptic spike event. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios and most of the current models in exhaustive learning experiments.

Keywords:Spiking neural network, event-driven STDP, continuous learning, deep learning, visual pattern recognition
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
G Mathematical and Computer Sciences > G730 Neural Computing
G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G700 Artificial Intelligence
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:31010
Deposited On:07 Mar 2018 12:38

Repository Staff Only: item control page