A Modified Error Function to Improve the Error Back-Propagation Algorithm for Multi-Layer Perceptrons

@inproceedings{Oh1995AME,
  title={A Modified Error Function to Improve the Error Back-Propagation Algorithm for Multi-Layer Perceptrons},
  author={Sang-Hoon Oh and Youngjik Lee},
  year={1995}
}
This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps.

Citations

Publications citing this paper.
SHOWING 1-8 OF 8 CITATIONS

Hybrid neural network for efficient training

  • 2017 International Conference on Electrical, Computer and Communication Engineering (ECCE)
  • 2017
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Analysis of learning rate using BP algorithm for hand written digit recognition application

  • 2010 International Conference on Information and Emerging Technologies
  • 2010
VIEW 2 EXCERPTS
CITES RESULTS

References

Publications referenced by this paper.
SHOWING 1-10 OF 14 REFERENCES

A Database for Handwritten Text Recognition Research

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1994
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

A double-well potentional energy function resolving bistable ambiguity figures by neural networks

H. H. Szu, F. Lu
  • Proc. WCNN, June 5-9, 1994, San Diego, USA, vol. III, pp. 426-431, 1994.
  • 1994

Classification of large set of handwritten characters using modified back propagation model

  • 1990 IJCNN International Joint Conference on Neural Networks
  • 1990
VIEW 2 EXCERPTS