Iterative Weighted Least Squares Algorithms for Neural Networks Classifiers

@inproceedings{Kurita1992IterativeWL,
  title={Iterative Weighted Least Squares Algorithms for Neural Networks Classifiers},
  author={Takio Kurita},
  booktitle={ALT},
  year={1992}
}
This paper discusses learning algorithms of layered neural networks from the standpoint of maximum likelihood estimation. Fisher information is explicitly calculated for the network with only one neuron. It can be interpreted as a weighted covariance matrix of input vectors. A learning algorithm is presented on the basis of Fisher's scoring method. It is shown that the algorithm can be interpreted as iterations of weighted least square method. Then those results are extended to the layered… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 19 extracted citations

Object Recognition by Integrated Information Using Web Images

2013 2nd IAPR Asian Conference on Pattern Recognition • 2013
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 10 references

On Maximum Likelihood Estimation of Feed-Forward Neural Net Parameters

T. Kurita
IEICE Tech. Report, • 1991
View 1 Excerpt

A Method to Determine the Number of Hidden Units of Three Layered Neural Networks by Information Criteria

T. Kurita
Trans. of IEICE Japan, • 1990
View 1 Excerpt

A probabilistic approach to the understanding and training of neural network classi ers

H. Gish
In Proceedings of IEEE Conference on Acoustics Speech and Signal Processing, • 1990
View 2 Excerpts

Convergence of back propagation in neural networks using a loglikelihood cost function, Electronics

M.J.J. Holt, S. Semanani
Letters, Vol.26, • 1990
View 2 Excerpts

Connectionist Learning Procedures

Artif. Intell. • 1989
View 3 Excerpts

Learning internal representations by error propagation, in Parallel Distributed Processing Volume 1, McCleland,J.L., Rumelhart,D.E., and The PDP

D. E. Rumelhart, G. E. Hinton, R. J. Williams
Research group, • 1986
View 1 Excerpt

Similar Papers

Loading similar papers…