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 AuthorJulian 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.

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.