Fast algorithms for the discrete cosine transformation
Computational Mathematics and Mathematical Physics
Orthogonal Transforms for Digital Signal Processing
Orthogonal Transforms for Digital Signal Processing
Automatic generation of fast discrete signal transforms
IEEE Transactions on Signal Processing
On Feature Extraction Capabilities of Fast Orthogonal Neural Networks
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Two-Dimensional Fast Orthogonal Neural Network for Image Recognition
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Digital watermarking enhancement using wavelet filter parametrization
ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I
Fractal learning of fast orthogonal neural networks
Optical Memory and Neural Networks
| Hi-index | 0.00 |
The paper presents a novel approach to the construction and learning of linear neural networks based on fast orthogonal transforms. The orthogonality of basic operations associated with the algorithm of a given transform is used in order to substantially reduce the number of adapted weights of the network. Two new types of neurons corresponding to orthogonal basic operations are introduced and formulas for architecture-independent error backpropagation and weights adaptation are presented.