 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| • |
Instead of
training one big neural net to deal with every
|
|
|
training case,
use several small neural nets.
|
|
|
|
– |
Each
small net is good at a particular subset of the
|
|
|
cases
|
|
|
|
– |
There
is a “manager” or “gating network” that decides
|
|
which
small net should be used for each case.
|
|
|
|
– |
The
gating net and the expert nets are all trained at
|
|
|
the
same time to minimize one big objective function.
|
|
|
| • |
This will be
covered in detail in the lecture on Oct 23.
|
|
|
|
– |
Meanwhile
you could read the 1991 paper called
|
|
|
“Adaptive
mixtures of local experts” on my webpage.
|
|