Off the Mainstream: Advances in Neural Networks and Machine Learning for Pattern Recognition

Trentin, Edmondo; Schwenker, Friedhelm; Gayar, Neamat El; Abbas, Hazem M.

doi:10.1007/s11063-018-9830-8

Cited by 9 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the remainder of the paper, ANNs will be used to refer to second-generation ANNs. Accordantly with what is previously said, off-the-mainstream approaches in neural networks and machine learning for pattern recognition have been recently encouraged [14] in Neural Processing Letters, with an entire special issue being devoted to various off-the-mainstream fields in pattern recognition (associative memories, density-related algorithms, etc.). We believe that the SNNs, being the third-generation of ANNs, as an alternative or a complement to traditional second-generation ANNs, definitely deserve attention when considering off-the-mainstream approaches in neural processing.…”

Section: Introductionmentioning

confidence: 76%

Spiking Neural Networks: Background, Recent Development and the NeuCube Architecture

Tan

Šarlija

Kasabov

2020

Neural Process Lett

View full text Add to dashboard Cite

This paper reviews recent developments in the still-off-the-mainstream information and data processing area of spiking neural networks (SNN)-the third generation of artificial neural networks. We provide background information about the functioning of biological neurons, discussing the most important and commonly used mathematical neural models. Most relevant information processing techniques, learning algorithms, and applications of spiking neurons are described and discussed, focusing on feasibility and biological plausibility of the methods. Specifically, we describe in detail the functioning and organization of the latest version of a 3D spatio-temporal SNN-based data machine framework called NeuCube, as well as it's SNN-related submodules. All described submodules are accompanied with formal algorithmic formulations. The architecture is highly relevant for the analysis and interpretation of various types of spatio-temporal brain data (STBD), like EEG, NIRS, fMRI, but we highlight some of the recent both STBD-and non-STBD-based applications. Finally, we summarise and discuss some open research problems that can be addressed in the future. These include, but are not limited to: application in the area of EEG-based BCI through transfer learning; application in the area of affective computing through the extension of the NeuCube framework which would allow for a biologically plausible SNN-based integration of central and peripheral nervous system measures. Matlab implementation of the NeuCube's SNN-related module is available for research and teaching purposes. Keywords Artificial neural networks • Spiking neural networks • Spike encoding • Spike-timing dependent plasticity • Spatio-temporal brain data • NeuCube

show abstract

Section: Introductionmentioning

confidence: 76%

Spiking Neural Networks: Background, Recent Development and the NeuCube Architecture

Tan

Šarlija

Kasabov

2020

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…One of the machine learning applications is pattern recognition. 38 , 51 Deep learning (also known as deep structured learning) is broadly applied in machine learning applications, especially pattern recognition 38 , 51 and has advantages in its flexibility to develop learning styles i.e., supervised, semi-supervised, or unsupervised. 33 , 34 Deep learning models have been chosen and deployed with independent testing datasets to measure their accuracy.…”

Section: Discussionmentioning

confidence: 99%

Universal closed-tube barcoding for monitoring the shark and ray trade in megadiverse conservation hotspots

et al. 2023

View full text Add to dashboard Cite

“…In the absence of an online reference database of elasmobranch fluorescent signatures, machine learning was developed for this study. One of the machine learning applications is pattern recognition (Jenrette et al, 2022;Trentin et al, 2018). Deep learning (also known as deep structured learning) is broadly applied in machine learning applications, especially pattern recognition (Jenrette et al, 2022;Trentin et al, 2018) and has advantages in its flexibility to develop learning styles i.e.…”

Section: Discussionmentioning

confidence: 99%

“…One of the machine learning applications is pattern recognition (Jenrette et al, 2022;Trentin et al, 2018). Deep learning (also known as deep structured learning) is broadly applied in machine learning applications, especially pattern recognition (Jenrette et al, 2022;Trentin et al, 2018) and has advantages in its flexibility to develop learning styles i.e. supervised, semi-supervised or unsupervised (LeCun et al, 2015;Malde et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Universal Closed-Tube Barcoding for Monitoring the Shark and Ray Trade in Megadiverse Conservation Hotspots

et al. 2022

View full text Add to dashboard Cite

Off the Mainstream: Advances in Neural Networks and Machine Learning for Pattern Recognition

Cited by 9 publications

References 21 publications

Spiking Neural Networks: Background, Recent Development and the NeuCube Architecture

Spiking Neural Networks: Background, Recent Development and the NeuCube Architecture

Universal closed-tube barcoding for monitoring the shark and ray trade in megadiverse conservation hotspots

Universal Closed-Tube Barcoding for Monitoring the Shark and Ray Trade in Megadiverse Conservation Hotspots

Contact Info

Product

Resources

About