by Open Science Repository Computer and Information Sciences
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.
Full textHypercube Neuron
Click here to post comments
Return to journal abstracts.