Can I read On the Perceptron Learning Algorithm on Data with High Precision on EtoBox?

On the Perceptron Learning Algorithm on Data with High Precision by Kai-Yeung Siu; Amir Dembo; Thomas Kailath is a Computer Science article available to read on EtoBox.

What is On the Perceptron Learning Algorithm on Data with High Precision about?

We investigate the convergence rate of the perceptron algorithm when the patterns are given with high precision. In particular, using the result of A. Dembo (Quart. AppL Math. 47 (1989), 185-195), we show that when the n pattern vectors are independent and uniformly distributed over { + 1, -1 }nlogn, as n --\* oe, with high probability, the patterns can be classified into all 2 ~ possible ways using perceptron algorithm with O(n log n) iteration. Further, the storage of parameters requires only O(n log 2 n) bits. We also indicate some interesting mathematical connections with the theory of random matrices.

Who reads On the Perceptron Learning Algorithm on Data with High Precision?

Author

Kai-Yeung Siu; Amir Dembo; Thomas Kailath

Publisher

Elsevier Science; Elsevier ; Elsevier Inc.; Elsevier BV (ISSN 0022-0000)

Published

1994

Language

EN

Field

Computer Science (Physical Sciences)