- ... Schmidhuber1
- Current address:
Dept. of Computer Science,
University of Colorado,
Campus Box 430,
Boulder, CO 80309, USA, yirgan@cs.colorado.edu
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
- ... inputs2
- Recently I became aware that Don Mathis
had some related ideas (personal communication). A hierarchical
approach to
sequence generation was pursued by [Miyata, 1988].
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
- ... well3
- For instance, we might employ the
more limited feedforward networks and a `time window' approach. In this case,
the number of previous inputs to be considered as a basis for the next
prediction will remain fixed.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
- ... step4
- A unique time representation is
theoretically necessary to provide with unambiguous
information about when the failure occurred (see also the last
paragraph of section 2). A unique representation of the time
that went by since the last unpredicted input occurred will do as well.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
- ... description5
- In contrast,
the reduced
descriptions referred to by [Mozer, 1990] are not unambiguous.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.