Optimal parameters selection of back propagation algorithm in the feedforward neural network

DOI10.1016/J.ENGANABOUND.2023.03.033zbMath1521.65055MaRDI QIDQ6158709

No author found.

Publication date: 20 June 2023

Published in: Engineering Analysis with Boundary Elements (Search for Journal in Brave)

zbMATH Keywords

convergenceefficiencyloss functionimproved back propagation algorithmoptimal weights and thresholds

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical optimization and variational techniques (65K10)

Cites Work

• Unnamed Item
• Accurate cyclic plastic analysis using a neural network material model
• Backpropagation and stochastic gradient descent method
• Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces
• On the variational principle
• Global convergence of Newton's method on an interval
• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• Data-driven multi-scale multi-physics models to derive process-structure-property relationships for additive manufacturing
• Domains of global convergence for Newton's method from auxiliary points
• A meshfree stabilized collocation method (SCM) based on reproducing kernel approximation
• A weighted meshfree collocation method for incompressible flows using radial basis functions
• Improved adaptive genetic algorithm for the vehicle insurance fraud identification model based on a BP neural network
• A meshfree method for inverse wave propagation using collocation and radial basis functions
• A Computational Mechanics special issue on: Data-driven modeling and simulation -- theory, methods, and applications
• Machine learning: Trends, perspectives, and prospects
• Subdomain radial basis collocation method for fracture mechanics
• Weighted radial basis collocation method for boundary value problems
• A combined genetic and eigensensitivity algorithm for the location of damage in structures
• Direct collocation method for identifying the initial conditions in the inverse wave problem using radial basis functions
• A physics-informed neural network technique based on a modified loss function for computational 2D and 3D solid mechanics

This page was built for publication: Optimal parameters selection of back propagation algorithm in the feedforward neural network