The Improved Training Algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate

@article{Li2009TheIT,
  title={The Improved Training Algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate},
  author={Y. Li and Y. Fu and H. Li and S. Zhang},
  journal={2009 International Conference on Computational Intelligence and Natural Computing},
  year={2009},
  volume={1},
  pages={73-76}
}
  • Y. Li, Y. Fu, +1 author S. Zhang
  • Published 2009
  • Computer Science
  • 2009 International Conference on Computational Intelligence and Natural Computing
This paper addresses the questions of improving convergence performance for back propagation (BP) neural network. For traditional BP neural network algorithm, the learning rate selection is depended on experience and trial. In this paper, based on Taylor formula the function relationship between the total quadratic training error change and connection weights and biases changes is obtained, and combined with weights and biases changes in batch BP learning algorithm, the formula for self… Expand
View on IEEE
doi.org
54 Citations
Highly Influential Citations
2
Background Citations
12
Methods Citations
18

54 Citations

Citation Type

Citation Type

Weights adjustment of two-term back-propagation network using adaptive and fixed learning methods
  • 2
Improving Error Back Propagation Algorithm by using Cross Entropy Error Function and Adaptive Learning Rate
  • 4
A novel strategy for speed up training for back propagation algorithm via dynamic adaptive the weight training in artificial neural network
  • 2
  • PDF
Training neural network with damped oscillation and maximized gradient function
  • 2
Dynamically-adaptive Weight in Batch Back Propagation Algorithm via Dynamic Training Rate for Speedup and Accuracy Training
  • 2
  • PDF
Fuzzy Wavelet Neural Network With an Accelerated Hybrid Learning Algorithm
  • 94
Beyond back-propagation learning for diabetic detection: Convergence comparison of gradient descent, momentum and Adaptive Learning Rate
  • 5
An Adaptive Neural Network for Email Spam Classification
A Joint Optimization of Momentum Item and Levenberg-Marquardt Algorithm to Level Up the BPNN’s Generalization Ability
  • 1
  • PDF
Optimizing Deep Feedforward Neural Network Architecture: A Tabu Search Based Approach
  • 5
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-9 OF 9 REFERENCES
The improvements of BP neural network learning algorithm
  • W. Jin, Z. Li, L. Wei, Han Zhen
  • Computer Science
  • WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000
  • 2000
  • 157
Convergence of Batch BP Algorithm with Penalty for FNN Training
  • 29
  • PDF
A Hybrid Training Algorithm for Feedforward Neural Networks
  • 28
A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis
  • Haibin Cai, Liangxu Liu, Qiying Cao
  • Mathematics, Computer Science
  • First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06)
  • 2006
  • 4
Parameter effects on convergence speed and generalization capability of backpropagation algorithm
  • 17
Cryptand/metal ion coated piezoelectric quartz crystal sensors with artificial back propagation neural network analysis for nitrogen dioxide and carbon monoxide
  • 16
Learning internal representations by error propagation
  • 18,432
  • PDF
Cryptand/metalion coated piezoelectric quartz crystal sensors with artificial back propagation neural network analysis for nitrogen dioxide and carbon monoxide
  • Sensors and Actuators B: Chemical, vol. 106, Apr. 2005, pp.468–476, doi: 10.1016/j.snb.2004.09.009.
  • 2005
Convergence of batch bp
  • Convergence of batch bp