-
Improved visualization of cost landscape for an ensemble of nets
-
-
-
(rather than best predicted point)
-
Train an ensemble of nets simultaneously
-
-
Previously if the number of nets was greater than the generation num then we wouldn't train the extra nets.
-
-
-
-
-
-
-
Previously this didn't really work, because if you constructed multiple nets in quick succession they'd save over each other. Now the filenames have a few random bytes in them, so this shouldn't be a problem any more.
-
-
-
https://github.com/charmasaur/M-LOOP
… nntesting
-
-
-
-
This means we can do things like cycle through nets per generation, interleave param generation and training of those nets, and so on. We can probably remove the sampling from the net itself now.
-
-
-
-
On python 2 math.ceil returns a float, and this was making range unhappy.
-
-
-
-
Add "training" logging to all training runs
-
-
Log learner type with run number
-
-
Fix NN exception on python 2
-
On python 2 math.ceil returns a float, and this was making range unhappy.
-
Import neural net changes from charmasaur