Learning as Extraction of Low-dimensional Representations

@inproceedings{Edelman1996LearningAE,
  title={Learning as Extraction of Low-dimensional Representations},
  author={Shimon Edelman and Nathan Intrator},
  year={1996}
}
Psychophysical ndings accumulated over the past several decades indicate that perceptual tasks such as similarity judgment tend to be performed on a low-dimensional representation of the sensory data. Low dimensionality is especially important for learning, as the number of examples required for attaining a given level of performance grows exponentially with the dimensionality of the underlying representation space. In this chapter, we argue that, whereas many perceptual problems are tractable… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 54 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 76 references

Similarity to reference shapes as a basis for shaperepresentationShimon

EdelmanFlorin CutzuSharon Duvdevani-BarDept
1996
View 5 Excerpts
Highly Influenced

Exploratory projection pursuit

J. H. Friedman
Journal of the American Statistical Asso- • 1987
View 3 Excerpts
Highly Influenced

Asymptotics of graphical projection pursuit

P. Diaconis, D. Freedman
Annals of • 1984
View 4 Excerpts
Highly Influenced

Multidimensional scaling, tree-fitting, and clustering.

Science • 1980
View 6 Excerpts
Highly Influenced

Color, hue, and wavelength

R. M. Boynton
Carterette, E. C. and Friedman, M. P., • 1978
View 5 Excerpts
Highly Influenced

Pattern classification and scene analysis

A Wiley-Interscience publication • 1973
View 3 Excerpts
Highly Influenced

Spectral distribution of typical daylight

D. B. Judd, D. L. MacAdam, G. Wyszecki
1964
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…