Solving the linear interval tolerance problem for weight initialization of neural networks

DOI10.1016/j.neunet.2014.02.006zbMath1323.92012OpenAlexW2101877290WikidataQ45014587 ScholiaQ45014587MaRDI QIDQ2339407

George D. Magoulas, D. A. Karras, Stavros P. Adam, Michael N. Vrahatis

Publication date: 1 April 2015

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://eprints.bbk.ac.uk/id/eprint/13757/1/LIT-Approach-web.pdf

zbMATH Keywords

neural networksinterval analysislinear interval tolerance problemweight initialization

Mathematics Subject Classification ID

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

Related Items (1)

A frequency-domain approach to improve ANNs generalization quality via proper initialization

Uses Software

• UCI-ml
• SPSS
• MNIST
• p.adjust

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• New techniques for the analysis of linear interval equations
• Comparison of the Hansen-Sengupta and the Frommer-Lang-Schnurr existence tests
• Derived eigenvalues of symmetric matrices, with applications to distance geometry
• Novel global robust stability criteria for interval neural networks with multiple time-varying delays
• Fuzzy sets as a basis for a theory of possibility
• Solving linear interval systems is NP-hard even if we exclude overflow and underflow
• Computational complexity and feasibility of data processing and interval computations
• Interval analysis: Theory and applications
• Linear interval tolerance problem and linear programming techniques
• A new technique in systems analysis under interval uncertainty and ambiguity
• An application of interval methods to stock market forecasting
• Solving overdetermined systems of interval linear equations
• Newton-Algorithmen zur Bestimmung von Nullstellen mit Fehlerschranken
• Guaranteed parameter set estimation for exponential sums: the three-terms case
• Intrinsic Dimensionality Estimation of High-Dimension, Low Sample Size Data withD-Asymptotics
• An Algorithm for Least-Squares Estimation of Nonlinear Parameters
• Bounding the Solution of Interval Linear Equations
• A Comparison of some Methods for Solving Linear Interval Equations
• Solvability of Systems of Linear Interval Equations
• An analysis of variance test for normality (complete samples)
• The high-dimension, low-sample-size geometric representation holds under mild conditions
• Self-validating methods

This page was built for publication: Solving the linear interval tolerance problem for weight initialization of neural networks