An Exactly Solvable Model of Unsupervised Learning

  title={An Exactly Solvable Model of Unsupervised Learning},
  author={Niels Bohr InstituteBlegdamsvej}
  • Niels Bohr InstituteBlegdamsvej
A model for unsupervised learning from N {dimensional data is studied. Random training examples are drawn such that the distribution of their overlaps with a vector B 2 IR N is a mixture of two Gaussians of unit width and a separation. A student vector is generated by an online algorithm, using each example only once. The evolution of its overlap with B can be calculated exactly in the thermodynamic limit N ! 1. As a speciic example, a learning algorithm closely related to Oja's rule is… CONTINUE READING


Publications referenced by this paper.
Showing 1-2 of 2 references

Mean Square optimality in the continous time RobbinsMonro procedure " , Technical Report DRB306

  • J. E. Moody, S. J. Hanson, R. P. Lippmann
  • 1992

The Statistical Mechanics of Learning a Rule

  • A. Rau, M. Biehl
  • Phys . Rev . A
  • 1992

Similar Papers

Loading similar papers…