Blick ins Buch

Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons

Julian Knaup (Autor)

Buch | Softcover

XII, 77 Seiten

2022 | 1st ed. 2022
Springer Fachmedien Wiesbaden GmbH (Verlag)
978-3-658-38954-3 (ISBN)

Lese- und Medienproben

Inhaltsverzeichnis (PDF)

Artikel merken

Multilayer neural networks based on multi-valued neurons (MLMVNs) have been proposed to combine the advantages of complex-valued neural networks with a plain derivative-free learning algorithm. In addition, multi-valued neurons (MVNs) offer a multi-valued threshold logic resulting in the ability to replace multiple conventional output neurons in classification tasks. Therefore, several classes can be assigned to one output neuron. This book introduces a novel approach to assign multiple classes to numerous MVNs in the output layer. It was found that classes that possess similarities should be allocated to the same neuron and arranged adjacent to each other on the unit circle. Since MLMVNs require input data located on the unit circle, two employed transformations are reevaluated. The min-max scaler utilizing the exponential function, and the 2D discrete Fourier transform restricting to the phase information for image recognition. The evaluation was performed on the Sensorless Drive Diagnosis dataset and the Fashion MNIST dataset.

lt;b>Julian Knaup received his B. Sc. in Electrical Engineering and his M. Sc. in Information Technology from the University of Applied Sciences and Arts Ostwestfalen-Lippe. He is currently working on machine learning algorithms at the Institute Industrial IT and researching AI potentials in product creation.

1 Introduction.- 2 Preliminaries.- 3 Scientific State of the Art.- 4 Approach.- 5 Evaluation.- 6 Conclusion and Outlook.

Erscheinungsdatum	09.08.2022
Reihe/Serie	BestMasters
Zusatzinfo	XII, 77 p. 44 illus.
Verlagsort	Wiesbaden
Sprache	englisch
Maße	148 x 210 mm
Gewicht	131 g
Themenwelt	Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
Themenwelt	Mathematik / Informatik ► Mathematik ► Analysis
Schlagworte	Class Assignment • classification • Complex-Valued • CVNN • Fourier transform • machine learning • MLMVN • Multi-Valued Neurons • MVN • Neural networks • Phase
ISBN-10	3-658-38954-0 / 3658389540
ISBN-13	978-3-658-38954-3 / 9783658389543
Zustand	Neuware