Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons / by Julian Knaup.

Format:

Book

Author/Creator:

Knaup, Julian., Author.

Contributor:

SpringerLink (Online service)

Series:

Computer Science (SpringerNature-11645)

BestMasters 2625-3615

BestMasters, 2625-3615

Language:

English

Subjects (All):

Artificial intelligence.

Machine learning.

Mathematics-Data processing.

Artificial Intelligence.

Machine Learning.

Computational Science and Engineering.

Local Subjects:

Artificial Intelligence.

Machine Learning.

Computational Science and Engineering.

Physical Description:

1 online resource (XII, 77 pages) : 44 illustrations

Edition:

1st ed. 2022.

Contained In:

Springer Nature eBook

Place of Publication:

Wiesbaden : Springer Fachmedien Wiesbaden : Imprint: Springer Vieweg, 2022.

System Details:

text file PDF

Summary:

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.

Contents:

1 Introduction

2 Preliminaries

3 Scientific State of the Art

4 Approach

5 Evaluation

6 Conclusion and Outlook.

Other Format:

Printed edition:

ISBN:

978-3-658-38955-0

9783658389550

Access Restriction:

Restricted for use by site license.