(

**Jürgen
Schmidhuber ^{1}
Technische Universität
München
**

The RTRL
algorithm for fully recurrent continually running
networks [Robinson and Fallside, 1987][Williams and Zipser, 1989]
requires computations per time step,
where is the number of non-input units. I
describe a method suited for on-line learning which computes exactly
the same gradient and requires
fixed-size storage of the same order
but has an average
time complexity^{2}per time step of .

Juergen Schmidhuber 2003-02-13

Back to Recurrent Neural Networks page