Re:Machine-Learning Maestro Michael Jordan on the Delusions ...
by asdavis on Tuesday October 21, 2014 @12:25PM
(#8488107)
It looks like there are still reverse signals (eg., deltas), but they are multiplied by a random matrix B instead of the usual transpose of the weight matrix for that layer. Am I misunderstanding?
[ Parent
| on HN ]
There are no comments on this comment yet.