... Schmidhuber¹

Current address: Dept. of Computer Science, University of Colorado, Campus Box 430, Boulder, CO 80309, USA, yirgan@cs.colorado.edu

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

... complexity²

Since the acceptance of this paper for publication it has come to my attention that the same algorithm was derived by Ron Williams [Williams, 1989,Williams and Zipser, 1994].

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

... step³

Pineda has described another recurrent net algorithm which, as he states, "has some of the worst features of both algorithms" [Pineda, 1990]. His algorithm requires $\geq O(n^4)$ memory and $\geq O(n^4)$ computations per time step, if the number of time steps exceeds $n$.

.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

Back to Recurrent Neural Networks page