Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons (BestMasters) - Softcover

Knaup, Julian

 
9783658389543: Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons (BestMasters)
Softcover
ISBN 10: 3658389540 ISBN 13: 9783658389543
Publisher: Springer Vieweg, 2022

Synopsis

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.

"synopsis" may belong to another edition of this title.

About the Author

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.

From the Back Cover

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.


About the Author
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.

"About this title" may belong to another edition of this title.

Publisher
Springer Vieweg
Publication date
2022
Language
English
ISBN 10 
3658389540
ISBN 13 
9783658389543
Binding
Paperback
Edition number
1
Number of pages
89

Other Popular Editions of the Same Title

9783658389567: Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons

Featured Edition

ISBN 10:  3658389567 ISBN 13:  9783658389567
Publisher: Springer Vieweg, 2022
Softcover