Skip to main content

back to basics - static

Created on September 5|Last edited on September 11
plasticity is uniform dist, 0 to 2.

0100200300400500Step2
0.01 0.000001
0.01 1.0000e-7
0.01 1.0000e-8
Run set
4


other lr

Run set
4

try 0 to 10.

Run set
3

try exp -2 to 4

Run set
2

set a minimum plast.

Run set
2


Static plasticity. Randomly initialized. DFA weights are normally distributed now. Sigmoid activation to avoid exploding gradients (the main problem I've been dealing with for months).
I suspect that the majority of stability is provided by the new activation. It's rather a drastic choice.

Run set
39

test the limits of how high and how wide the range plasticity can be.

Run set
48

what about a normal distribution of values?

Run set
6

chill out. no need for exp() on the plasticity values. the distribution can be less extreme.

Run set
17