Mental representations are probabilistic algorithms, often w loops and backtracking. Most learning paradigms produce only feedforward models
-
-
Replying to @Plinz
I'm under impression is what gives evolution based learning paired with guess/check modeling an edge - jumps out of local minimums easier?
1 reply 0 retweets 1 like
Replying to @ultimape
Perhaps we can find a more general learning strategy that discovers gradient descent as a sub solution where appropriate?
3:32 PM - 22 Sep 2017
0 replies
0 retweets
1 like
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.