Training feedforward networks with the Marquardt algorithm

1994/01/01 by M.T. Hagan, Martin Hagan, M.B. Menhaj +1 · 8 citations
Computer Science · #Blind Source Separation Techniques #Machine Learning and ELM #Neural Networks and Applications

paper · doi:10.1109/72.329697

openalex publication_date 1994/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the other techniques when the network contains no more than a few hundred weights.

Citations

• On the limited memory BFGS method for large scale optimization

Cited by

• Strategies for CFD Investigation and Optimization of the External Aerodynamics of a Sounding Rocket
• A general backpropagation algorithm for feedforward neural networks learning
• Fractional-order Backpropagation Neural Networks: Modified Fractional-order Steepest Descent Method for Family of Backpropagation Neural Networks
• Prediction of activation energy barrier of island diffusion processes using data-driven approaches
• Computationally Efficient CFD Prediction of Bubbly Flow using Physics-Guided Deep Learning
• Optimal Convergence Rate in Feed Forward Neural Networks using HJB\n Equation
• Predictive modelling of football injuries
• Policy Design for Active Sequential Hypothesis Testing using Deep\n Learning