A Solution for the N-bit Parity Problem Using a Single Translated Multiplicative Neuron
Neural Processing Letters
Nonlocal Estimation of Manifold Structure
Neural Computation
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
A new methodology of extraction, optimization and application of crisp and fuzzy logical rules
IEEE Transactions on Neural Networks
A Comparison of Methods for Learning of Highly Non-separable Problems
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Comparison of Shannon, Renyi and Tsallis Entropy Used in Decision Trees
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Support Vector Machines for Visualization and Dimensionality Reduction
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Projection Pursuit Constructive Neural Networks Based on Quality of Projected Clusters
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Constrained Learning Vector Quantization or Relaxed k-Separability
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Almost Random Projection Machine
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Support feature machine for DNA microarray data
RSCTC'10 Proceedings of the 7th international conference on Rough sets and current trends in computing
Almost random projection machine with margin maximization and kernel features
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Hi-index | 0.00 |
Learning problems with inherent non-separable Boolean logic is still a challenge that has not been addressed by neural or kernel classifiers. The k-separability concept introduced recently allows for characterization of complexity of non-separable learning problems. A simple constructive feedforward network that uses a modified form of the error function and a window-like functions to localize outputs after projections on a line has been tested on such problems with quite good results. The computational cost of training is low because most nodes and connections are fixed and only weights of one node are modified at each training step. Several examples of learning Boolean functions and results of classification tests on real-world multiclass datasets are presented.