A joint optimization of momentum item and Levenberg-Marquardt algorithm to level up the BPNN's generalization ability (Q1718873): Difference between revisions
From MaRDI portal
Set OpenAlex properties. |
ReferenceBot (talk | contribs) Changed an Item |
||
Property / cites work | |||
Property / cites work: Robust adaptive learning of feedforward neural networks via LMI optimizations / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q3609598 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Training the random neural network using quasi-Newton methods / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: A New Conjugate Gradient Method with Guaranteed Descent and an Efficient Line Search / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: A new convex objective function for the supervised learning of single-layer neural networks / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: An Algorithm for Least-Squares Estimation of Nonlinear Parameters / rank | |||
Normal rank |
Latest revision as of 03:35, 18 July 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | A joint optimization of momentum item and Levenberg-Marquardt algorithm to level up the BPNN's generalization ability |
scientific article |
Statements
A joint optimization of momentum item and Levenberg-Marquardt algorithm to level up the BPNN's generalization ability (English)
0 references
8 February 2019
0 references
Summary: Back propagation neural network (BPNN) as a kind of artificial neural network is widely used in pattern recognition and trend prediction. For standard BPNN, it has many drawbacks such as trapping into local optima, oscillation, and long training time. Because training the standard BPNN is based on gradient descent method, and the learning rate is fixed. Momentum item and Levenberg-Marquardt (LM) algorithm are two ways to adjust the weights among the neurons and improve the BPNN's performance. However, there is still much space to improve the two algorithms. The hybrid optimization of damping factor of LM and the dynamic momentum item is proposed in this paper. The improved BPNN is validated by Fisher Iris data and wine data. Then, it is used to predict the visit\(\_\)spend. The database is provided by Dunnhumby's Shopper Challenge. Compared with the other two improved BPNNs, the proposed method gets a better performance. Therefore, the proposed method can be used to do the pattern recognition and time series prediction more effectively.
0 references
0 references