articleTop 1% cited
Training feedforward networks with the Marquardt algorithm
IEEE Transactions on Neural Networks · 1994 · Vol. 5(6) · pp. 989–993
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.
Neural Networks and ApplicationsMachine Learning and ELMBlind Source Separation TechniquesBackpropagationAlgorithmLevenberg–Marquardt algorithmArtificial neural networkRpropConjugate gradient methodComputer scienceFeedforward neural networkArtificial intelligenceFunction (biology)
Citations
7,665
FWCI
14.15
field-weighted impact
References
19
Percentile
99%
vs. same field & year
Citations per year
Cited by
Selection of Proper Neural Network Sizes and Architectures—A Comparative Study
IEEE Transactions on Industrial Informatics · 2012 · 413 citations
Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm
Applied Mathematics and Computation · 2012 · 503 citations
Artificial Neural Network and Support Vector Machine Approach for Locating Faults in Radial Distribution Systems
IEEE Transactions on Power Delivery · 2005 · 410 citations
Freeway Travel Time Prediction with State-Space Neural Networks: Modeling State-Space Dynamics with Recurrent Neural Networks
Transportation Research Record Journal of the Transportation Research Board · 2002 · 284 citations
Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm
IEEE Transactions on Intelligent Transportation Systems · 2011 · 425 citations
On field calibration of an electronic nose for benzene estimation in an urban pollution monitoring scenario
Sensors and Actuators B Chemical · 2007 · 535 citations
State-of-the-art in artificial neural network applications: A survey
Heliyon · 2018 · 2,936 citations
Trends in extreme learning machines: A review
Neural Networks · 2014 · 1,724 citations
References
Learning representations by back-propagating errors
Nature · 1986 · 30,045 citations
First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method
Neural Computation · 1992 · 1,192 citations
Increased rates of convergence through learning rate adaptation
Neural Networks · 1988 · 1,797 citations
Related articles
Training feedforward networks with the Marquardt algorithm
IEEE Transactions on Neural Networks · 1994 · 7,665 citations
Citation Network
How this paper connects to the literature. Drag to explore, click any node to open that paper.