Applying SP-MLP to complex classification problems
Pattern Recognition Letters
The constraint based decomposition (CBD) training architecture
Neural Networks
Classification ability of single hidden layer feedforward neural networks
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
A two-layer paradigm capable of forming arbitrary decision regions in input space
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In this paper, the author theoretically discusses the partitioning capabilities of the up-down algorithm and proves the implementation feasibility of the algorithm. Four propositions are presented in the paper. The first three propositions explain the nature of the up-down algorithm and the last one proves the implementation feasibility of the algorithm. The author also discusses the implementation feasibility of the partially nested rectangular decision regions using the proposed algorithm.