SourceForge.net Logo

... DIKU1
DIKU: Datalogisk Institut Københavns Universitet, Department of Computer Science University of Copenhagen
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... compiler2
In gcc it is possible to get signals when a overflow occurs with -ftrapv, but unfortunately some optimized pointer arithmetic in gcc makes integer overflow and breaks this functionality (see http://gcc.gnu.org/bugzilla/show_bug.cgi?id=1823).
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... aliasing3
C and C++ automaticly thinks that data reached from two different pointers could be the same. This makes for safe but slow code (FORTRAN assumes the opposite, which makes for fast unsafe code).
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... layer4
Actually this is a past the end pointer, which points to the layer one position past the last layer. But it is easier to think of it as a pointer to the last layer.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... epochs5
During one epoch each of the training pairs are trained for one iteration.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
... 0.756
The actual connection rate may be different, because some connections should always be in place.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.