Modified fractional-order steepest descent enables fractional-order backpropagation neural networks with claimed superior multi-scale global optimization over standard first-order BPNNs.
As we know, multilayer networks can be used to approximate virtually any function if we have a sufficient number of neurons in the hidden layers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fractional-order Backpropagation Neural Networks: Modified Fractional-order Steepest Descent Method for Family of Backpropagation Neural Networks
Modified fractional-order steepest descent enables fractional-order backpropagation neural networks with claimed superior multi-scale global optimization over standard first-order BPNNs.