國立高雄大學圖資館 |

Impact of class assignment on multinomial classification using multi-valued neurons

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Impact of class assignment on multinomial classification using multi-valued neuronsby Julian Knaup.
作者:	Knaup, Julian.
出版者:	Wiesbaden :Springer Fachmedien Wiesbaden :2022.
面頁冊數:	xii, 77 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Neural networks (Computer science)
電子資源:	https://doi.org/10.1007/978-3-658-38955-0
ISBN:	9783658389550$q(electronic bk.)

Impact of class assignment on multinomial classification using multi-valued neurons
Knaup, Julian.

Impact of class assignment on multinomial classification using multi-valued neurons[electronic resource] /by Julian Knaup. - Wiesbaden :Springer Fachmedien Wiesbaden :2022. - xii, 77 p. :ill., digital ;24 cm. - BestMasters,2625-3615. - BestMasters..

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

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.

ISBN: 9783658389550$q(electronic bk.)

Standard No.: 10.1007/978-3-658-38955-0doiSubjects--Topical Terms:

181982
Neural networks (Computer science)

LC Class. No.: QA76.87 / .K53 2022

Dewey Class. No.: 006.32

Impact of class assignment on multinomial classification using multi-valued neurons
LDR:02505nmm a2200325 a 4500 001 628881
003 DE-He213
005 20220806213103.0
007 cr nn 008maaau
008 230224s2022 gw s 0 eng d
020 $a 9783658389550$q(electronic bk.)
020 $a 9783658389543$q(paper)
024 7 $a 10.1007/978-3-658-38955-0 $2 doi
035 $a 978-3-658-38955-0
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.87 $b .K53 2022
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.32 $2 23
090 $a QA76.87 $b .K67 2022
100 1 $a Knaup, Julian. $3 933361
245 1 0 $a Impact of class assignment on multinomial classification using multi-valued neurons $h [electronic resource] / $c by Julian Knaup.
260 $a Wiesbaden : $b Springer Fachmedien Wiesbaden : $b Imprint: Springer Vieweg, $c 2022.
300 $a xii, 77 p. : $b ill., digital ; $c 24 cm.
490 1 $a BestMasters, $x 2625-3615
505 0 $a 1 Introduction -- 2 Preliminaries -- 3 Scientific State of the Art -- 4 Approach -- 5 Evaluation -- 6 Conclusion and Outlook.
520 $a 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.
650 0 $a Neural networks (Computer science) $3 181982
650 1 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Machine Learning. $3 833608
650 2 4 $a Computational Science and Engineering. $3 274685
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a BestMasters. $3 676593
856 4 0 $u https://doi.org/10.1007/978-3-658-38955-0
950 $a Computer Science (SpringerNature-11645)