Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons by Julian Knaup
English | PDF | 2022 | 89 Pages | ISBN : 3658389540 | 2.7 MB
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.