Efficient Initialization of Artificial Neural Network Weights for Electrical Component Models

DOI10.1007/978-3-540-71980-9_15MaRDI QIDQ5432129zbMATH OpenOpenAlexFDO

Authors Tuomo Kujanpää, Janne Roos

Publication date 2 January 2008

Published in Scientific Computing in Electrical Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-540-71980-9_15

zbMATH Keywords

artificial neural networkmulti-layer perceptronweight-initialization methods

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Basic methods for problems in optics and electromagnetic theory (78M99) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Efficient methods of initializing neuron weights in self-organizing networks implemented in hardware
• Algorithm of choosing initialized weights for training complex-valued neural networks
• Structural, Syntactic, and Statistical Pattern Recognition
• A new initialization method for neural networks with weight sharing
• scientific article; zbMATH DE number 1859688
• A mathematical framework for improved weight initialization of neural networks using Lagrange multipliers
• A weight initialization based on the linear product structure for neural networks

Cited in

(3)

• Creating a model of passive electronic components using a neural network approach
• Efficient methods of initializing neuron weights in self-organizing networks implemented in hardware
• scientific article; zbMATH DE number 1859689 (Why is no real title available?)

This page was built for publication: Efficient Initialization of Artificial Neural Network Weights for Electrical Component Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5432129)