Classic perceptron is limited to classifying only data which is linearly separable. In this work it is proposed neuron that does not have that limitation. Using hypercube architecture it is possible to describe any logic function. Neuron using that kind of architecture can discover any logic function from train data. It is also possible to write into that kind of neuron any logic rule.
Keywords: Neuron, Hypercube, Multidimensional Activation Function, Neural Network, Hypercube Neuron.
Fialkiewicz, W. (2017). Hypercube Neuron. Open Science Repository Computer and Information Sciences, Online(open-access), 45011866e. http://doi.org/10.7392/OPENACCESS.45011866
Fialkiewicz, Wojciech. “Hypercube Neuron.” Open Science Repository Computer and Information Sciences Online.open-access (2017): 45011866e. Web. 26 Oct. 2017.
Fialkiewicz, Wojciech. “Hypercube Neuron.” Open Science Repository Computer and Information Sciences Online, no. open-access (October 26, 2017): 45011866e. doi:10.7392/OPENACCESS.45011866.
Fialkiewicz, W. (2017) ‘Hypercube Neuron’, Open Science Repository Computer and Information Sciences. Open Science Repository, Online(open-access), p. 45011866e. doi: 10.7392/OPENACCESS.45011866.
1. W. Fialkiewicz, Hypercube Neuron, Open Sci. Repos. Comput. Inf. Sci. Online, 45011866e (2017).
1. Fialkiewicz, W. Hypercube Neuron. Open Sci. Repos. Comput. Inf. Sci. Online, 45011866e (2017).
Research registered in the DOI resolution system as: 10.7392/openaccess.45011866.
Main criteria reviewers should evaluate are: originality, sound methodology and data, following of universal ethical principles, scientific relevance and clear description of problems, hypotheses and results.
Names, affiliations of reviewers and personal contacts should be included at the end of the text.
Maximum text length is 10000 characters. Only serious, consistent and original reviews are accepted.