Deep learning on Sleptsov nets

Sleptsov nets are applied as a uniform language to specify models of unconventional computations and artificial intelligence systems. A technique for specification of neural networks, including multidimensional and multilayer networks of deep learning approach, using Sleptsov nets, is shown; the way...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of parallel, emergent and distributed systems Jg. 36; H. 6; S. 535 - 548
Hauptverfasser: Shmeleva, Tatiana R., Owsiński, Jan W., Lawan, Abdulmalik Ahmad
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Abingdon Taylor & Francis 02.11.2021
Taylor & Francis Ltd
Schlagworte:
Artificial intelligence
Deep learning
gradient descend
mass parallel computations
Multilayers
Neural network
Neural networks
Optimization
Real numbers
sigmoid
Sleptsov net
ISSN:1744-5760, 1744-5779
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Sleptsov nets are applied as a uniform language to specify models of unconventional computations and artificial intelligence systems. A technique for specification of neural networks, including multidimensional and multilayer networks of deep learning approach, using Sleptsov nets, is shown; the ways of specifying basic activation functions by Sleptsov net are discussed, the threshold and sigmoid functions implemented. A methodology of training neural networks is presented with the loss function minimisation, based on a run of a pair of interacting Sleptsov nets, the first net implementing the neural network based on data flow approach, while the second net solves the optimisation task by adjusting the weights of the first net by the gradient descend method. The optimising net uses the earlier developed technology of programming in Sleptsov nets with reverse control flow and the subnet call technique. Real numbers and arrays are represented as markings of a single place of a Sleptsov net. Hyperperformance is achieved because of the possibility of implementing mass parallel computations.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1744-5760
1744-5779
DOI:10.1080/17445760.2021.1945055