Algorithm of choosing initialized weights for training complex-valued neural networks

zbMATH Open1171.68686MaRDI QIDQ3399792FDOQ3399792

Authors: Daiyuan Zhang 

Publication date: 12 October 2009

Recommendations

• Complex-valued recurrent neural network with IIR neuron model: Training and applications.
• An independent component analysis based weight initialization method for multilayer perceptrons
• On the inherent property of the decision boundary in complex-valued neural networks
• Convergence of batch split-complex backpropagation algorithm for complex-valued neural networks
• Convergence of an online split-complex gradient algorithm for complex-valued neural networks

zbMATH Keywords

artificial intelligencecomplex-valued neural networksfast learninghigh training accuracy

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cited In (5)

• An independent component analysis based weight initialization method for multilayer perceptrons
• Comparative analysis of the results of training a neural network with calculated weights and with random generation of the weights
• Efficient Initialization of Artificial Neural Network Weights for Electrical Component Models
• New Approach of Recurrent Neural Network Weight Initialization
• A meta-cognitive learning algorithm for a fully complex-valued relaxation network

This page was built for publication: Algorithm of choosing initialized weights for training complex-valued neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3399792)