Inversion of Fredholm integral equations of the first kind with fully connected neural networks

DOI10.1016/0016-0032(92)90031-BzbMath0759.65092OpenAlexW2141026751WikidataQ128111291 ScholiaQ128111291MaRDI QIDQ1188061

S. Singh

Publication date: 3 August 1992

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0016-0032(92)90031-b

zbMATH Keywords

numerical experimentsill-posed problemFredholm integral equations of the first kindfully connected neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Numerical methods for integral equations (65R20) Numerical methods for ill-posed problems for integral equations (65R30) Fredholm integral equations (45B05)

Related Items

Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields

Uses Software

• LINPACK

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• LINPACK
• An initial value method for solving Fredholm integral equation of the first kind
• On solving Fredholm integral equations of the first kind using the interval programming algorithm of Robers
• Improvement of the resolution of an instrument by numerical solution of an integral equation
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• High-resolution image reconstruction based on matrix inversion on a fully connected architecture
• A Technique for the Numerical Solution of Certain Integral Equations of the First Kind
• On Solving Fredholm Integral Equations of the First Kind
• On the Numerical Solution of Fredholm Integral Equations of the First Kind by the Inversion of the Linear System Produced by Quadrature
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.