The Cascade Orthogonal Neural Network

In the paper new non-conventional growing neural network is proposed. It coincides with the Cascade- Correlation Learning Architecture structurally, but uses ortho-neurons as basic structure units, which can be adjusted using linear tuning procedures. As compared with conventional approximating neural networks proposed approach allows significantly to reduce time required for weight coefficients adjustment and the training dataset size.

N–Dimensional Orthogonal Tile Sizing Problem

AMS subject classification: 68Q22, 90C90

Generalized Backscattering and the Lax-Phillips Transform

2000 Mathematics Subject Classification: 35P25, 35R30, 58J50.