An Unsupervised Approach to Learning and Early Detection of Spatio-Temporal Patterns Using Spiking Neural Networks

2015 ◽  
Vol 80 (S1) ◽  
pp. 83-97 ◽  
Author(s):  
Banafsheh Rekabdar ◽  
Monica Nicolescu ◽  
Richard Kelley ◽  
Mircea Nicolescu
Keyword(s):  
Neural Networks ◽  
Early Detection ◽  
Temporal Patterns ◽  
Spiking Neural Networks ◽  
Approach To Learning ◽  
Unsupervised Approach ◽  
Spatio Temporal

scholarly journals Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke

2014 ◽  
Vol 134 ◽  
pp. 269-279 ◽  
Author(s):  
Nikola Kasabov ◽  
Valery Feigin ◽  
Zeng-Guang Hou ◽  
Yixiong Chen ◽  
Linda Liang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Temporal Patterns ◽  
Spiking Neural Networks ◽  
Spatio Temporal

A Scale and Translation Invariant Approach for Early Classification of Spatio-Temporal Patterns Using Spiking Neural Networks

2015 ◽  
Vol 43 (2) ◽  
pp. 327-343 ◽  
Author(s):  
Banafsheh Rekabdar ◽  
Monica Nicolescu ◽  
Mircea Nicolescu ◽  
Mohammad Taghi Saffar ◽  
Richard Kelley
Keyword(s):  
Neural Networks ◽  
Temporal Patterns ◽  
Spiking Neural Networks ◽  
Translation Invariant ◽  
Early Classification ◽  
Spatio Temporal ◽  
Invariant Approach

scholarly journals Event-Based Trajectory Prediction Using Spiking Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Guillaume Debat ◽  
Tushar Chauhan ◽  
Benoit R. Cottereau ◽  
Timothée Masquelier ◽  
Michel Paindavoine ◽  
...  
Keyword(s):  
Neural Networks ◽  
Learning Rule ◽  
Temporal Patterns ◽  
Spike Timing ◽  
Spiking Neural Networks ◽  
Motion Features ◽  
Spatio Temporal ◽  
Event Based ◽  
Ball Trajectory ◽  
New Generation

In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory by adding a simple read-out layer composed of polynomial regressions, and trained in a supervised manner. Hence, we show that a SNN receiving inputs from an event-based sensor can extract relevant spatio-temporal patterns to process and predict ball trajectories.

Attentional Bias Pattern Recognition in Spiking Neural Networks from Spatio-Temporal EEG Data

2017 ◽  
Vol 10 (1) ◽  
pp. 35-48 ◽  
Author(s):  
Zohreh Gholami Doborjeh ◽  
Maryam G. Doborjeh ◽  
Nikola Kasabov
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Attentional Bias ◽  
Spiking Neural Networks ◽  
Eeg Data ◽  
Spatio Temporal
Sign in / Sign up

Export Citation Format

Share Document