登入選單
返回Google圖書搜尋
Impact of Class Assignment on Multinomial Classification Using Multi-Valued Neurons
Julian Knaup
出版Springer Nature, 2022-08-06
主題Computers / Artificial Intelligence / GeneralComputers / Computer ScienceComputers / Information TechnologyMathematics / Applied
ISBN36583895599783658389550
URLhttp://books.google.com.hk/books?id=y7Z_EAAAQBAJ&hl=&source=gbs_api
EBookSAMPLE
註釋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.