000 03342nam a22005415i 4500
001 978-3-658-38955-0
003 DE-He213
005 20240423130147.0
007 cr nn 008mamaa
008 220806s2022 gw | s |||| 0|eng d
020 _a9783658389550
_9978-3-658-38955-0
024 7 _a10.1007/978-3-658-38955-0
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
100 1 _aKnaup, Julian.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
245 1 0 _aImpact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons
_h[electronic resource] /
_cby Julian Knaup.
250 _a1st ed. 2022.
264 1 _aWiesbaden :
_bSpringer Fachmedien Wiesbaden :
_bImprint: Springer Vieweg,
_c2022.
300 _aXII, 77 p. 44 illus.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aBestMasters,
_x2625-3615
505 0 _a1 Introduction -- 2 Preliminaries -- 3 Scientific State of the Art -- 4 Approach -- 5 Evaluation -- 6 Conclusion and Outlook.
520 _aMultilayer 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 _aArtificial intelligence.
650 0 _aMachine learning.
650 0 _aMathematics
_xData processing.
650 1 4 _aArtificial Intelligence.
650 2 4 _aMachine Learning.
650 2 4 _aComputational Science and Engineering.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783658389543
776 0 8 _iPrinted edition:
_z9783658389567
830 0 _aBestMasters,
_x2625-3615
856 4 0 _uhttps://doi.org/10.1007/978-3-658-38955-0
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
942 _cSPRINGER
999 _c185715
_d185715