Abstract: 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.

Keywords: orthogonal activation functions, ortho-synapse, ortho-neuron, cascade orthogonal neural network.

ACM Classification Keywords: I.2.6 Learning – Connectionism and neural nets

Link:

THE CASCADE ORTHOGONAL NEURAL NETWORK

Yevgeniy Bodyanskiy, Artem Dolotov, Iryna Pliss, Yevgen Viktorov

http://www.foibg.com/ibs_isc/ibs-02/IBS-02-p02.pdf