@o_guest Q: about how many cycles did it take for ur recurrent maps to complete a partial pattern? :)
also TIL i have no croissant emoji ;(
-
-
Replying to @mattsiegel
Can you give me some context to this? Are we talking about my PhD work? It's mainly based on replicating a specific paper model.
1 reply 0 retweets 0 likes -
Replying to @o_guest @mattsiegel
*paper's – a paper model would b cool altho I'm sure paper flip flops would b hard to build altho by means impossible!
2 replies 0 retweets 1 like -
Replying to @o_guest @mattsiegel
it was done a while ago and it's a back prop through time network, not a map. I assume you mean a self-organising map?
1 reply 0 retweets 0 likes -
Replying to @o_guest @mattsiegel
I actually am not sure what you mean as self-organising maps don't settle. OK, i'll wait for you to clarify!
1 reply 0 retweets 0 likes -
Replying to @o_guest
ohhh, they don't settle?! :D i'm sorry; thank you for indulging my ignorance
1 reply 0 retweets 0 likes
I need help understanding what type of neural network this is. Back prop through time networks definitely settle when trained.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.