Skip to main content

No Recurrent Connection

Remove the recurrent connection. Try to get the rnn running, anyways, using weight updates for short-term memory. The plasticity value ought to be instrumental, here, some weights being more plastic than others and therefore changing quickly so as to store info.
Created on July 17|Last edited on July 25
Just look at the whole entire sweep. It's over learning rate, plasticity learning rate, and the batch size. I just wanna catch the high performers here, with the lowest loss numbers the fastest.

Showing first 29 runs
02k4k6kStep2.32.42.52.62.7
Run set
81

Which batch size seems to do the most? Is it really the batch size that I care about?

Run set
81

I really don't want learning rate to be the defining factor, here, but it seems like it wants to be. That's just gonna get us to the local minima of repeating the same input character back. No memory really needed for that, unfortunately.

Run set
81

I'd like to see this have a bigger influence. The plasticity learning rate ought to define how much plasticity values truly separate out short term and long term memory connections.

Run set
81

I want to know more about the batch size of 1. It's probably what's going to let me really encode memory in the weights.

Run set
21

some more drastic numbers

Run set
35

add some noise

Run set
10

add some noise, but include a different sort of initialization

Run set
10


only clip the weights


Run set
126



Run set
126



Run set
126



Run set
126



Run set
126



Run set
126



Run set
126