3 resultados para non-orthogonal sparsifying transform
em Bulgarian Digital Mathematics Library at IMI-BAS
Resumo:
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.
Resumo:
AMS subject classification: 68Q22, 90C90
Resumo:
2000 Mathematics Subject Classification: 35P25, 35R30, 58J50.