Truncated-Newton training algorithm for neurocomputational viscoplastic model.
From MaRDI portal
Publication:1418239
DOI10.1016/S0045-7825(03)00261-5zbMath1119.74622MaRDI QIDQ1418239
M. S. Al-Haik, H. Garmestani, I. Michael Navon
Publication date: 19 January 2004
Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)
Small-strain, rate-dependent theories of plasticity (including theories of viscoplasticity) (74C10) Neural networks for/in biological studies, artificial life and related topics (92B20) Optimization problems in solid mechanics (74P99)
Related Items
Computational water purification controls using second-order adjoint equations with stability confirmation ⋮ Bayesian regularization neural networks for optimizing fluid flow processes ⋮ Computational mechanics enhanced by deep learning ⋮ Molecular dynamics simulation of reorientation of polyethylene chains under a high magnetic field
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Block truncated-Newton methods for parallel optimization
- Assessing a search direction within a truncated Newton method
- A uniaxial viscoplastic model based on total strain and overstress
- Multilayer feedforward networks are universal approximators
- A truncated Newton optimization algorithm in meteorology applications with analytic Hessian/vector products
- A method of viscoelastic stress analysis using elastic solutions
- Truncated-Newton algorithms for large-scale unconstrained optimization
- Numerical Experience with Limited-Memory Quasi-Newton and Truncated Newton Methods
- Newton-Type Minimization via the Lanczos Method
- Preconditioning of Truncated-Newton Methods
- A Numerical Study of the Limited Memory BFGS Method and the Truncated-Newton Method for Large Scale Optimization
- Newton-type methods for unconstrained and linearly constrained optimization
- Numerical Optimization
- TNPACK—A truncated Newton minimization package for large-scale problems
- Function minimization by conjugate gradients