Deep learning with dense random neural networks

File Description SizeFormat 
DeepRNN.pdfSubmitted version327.01 kBAdobe PDFView/Open
Title: Deep learning with dense random neural networks
Authors: Gelenbe, E
Yin, Y
Item Type: Conference Paper
Abstract: We exploit the dense structure of nuclei to postulate that in such clusters, the neuronal cells will communicate via soma-to-soma interactions, aswell as through synapses. Using the mathematical structure of the spiking Random Neural Network, we construct a multi-layer architecture for Deep Learning. An efficient training procedure is proposed for this architecture. It is then specialized to multi-channel datasets, and applied to images and sensor-based data.
Editors: Gruca, A
Czachorski, T
Harezlak, K
Kozielski, S
Piotrowska, A
Issue Date: 20-Sep-2017
Date of Acceptance: 1-Sep-2017
URI: http://hdl.handle.net/10044/1/71116
DOI: https://doi.org/10.1007/978-3-319-67792-7_1
ISBN: 9783319677910
ISSN: 2194-5357
Publisher: Springer
Start Page: 3
End Page: 18
Journal / Book Title: Man-Machine Interactions 5, ICMMI 2017
Volume: 659
Copyright Statement: © 2018 Springer International Publishing AG.
Sponsor/Funder: European Commission
European Commission Directorate-General for Research and Innovation
EU H2020 Framework Programme for Research and Innovation
Funder's Grant Number: ICT-2013.1.2 - Software Engineering, Services and Cloud Computing
EU H2020 Framework Prog. R & Innovation Grant Agreement 727528
Conference Name: 5th International Conference on Man-Machine Interactions (ICMMI)
Keywords: Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Cybernetics
Computer Science, Theory & Methods
Computer Science
Deep learning
Neural network
Machine learning
VIDEO QUALITY
BIG
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Cybernetics
Computer Science, Theory & Methods
Computer Science
Deep learning
Neural network
Machine learning
VIDEO QUALITY
BIG
Publication Status: Published
Start Date: 2017-10-03
Finish Date: 2017-10-06
Conference Place: Krakow, Poland
Online Publication Date: 2017-09-20
Appears in Collections:Electrical and Electronic Engineering



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons