backprop/gradient descent, and if so what cost functions it optimizes, is very important regardless of whether a) turns out in the (6/14)
-
-
Replying to @AdamMarblestone @tyrell_turing and
affirmative or negative. Both of you do look closely at the neuroscience literature in these research programs. Why don't *others* (7/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
in the ML field look so closely -- I think because it is really hard, and the literature is still murky: we need much better (8/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
ground-truth cortical microcircuit and brain macro-circuit data, and we need to better curate the literature to have good answers (9/14)
1 reply 0 retweets 5 likes -
Replying to @AdamMarblestone @tyrell_turing and
to questions like "what does the neuroscience literature say about how the brain does prediction" agreed upon by more than 1 person (10/14)
1 reply 0 retweets 5 likes -
Replying to @AdamMarblestone @tyrell_turing and
at a time at best (most probably have ~no opinion because drawing general conclusions like this from neuroscience papers as they (11/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
stand requires quite some leaps of faith, or at least I haven't understood how to do so well yet). If Konrad is right about the (12/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
lack of *direct* interpretability of representations, we had better hope to understand in terms of cost functions, learning (13/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
algorithms, and their emergent effects... (14/14)
1 reply 0 retweets 5 likes -
Replying to @AdamMarblestone @dileeplearning and
Yup, I can agree with everything here! I thank you Adam for providing the appropriate cap to this discussion!pic.twitter.com/E6uTPVKgoC
1 reply 0 retweets 4 likes
Didn't mean to end it, just saying I enjoy it and it doesn't need to resolve in a binary fashion.
-
-
Replying to @AdamMarblestone @dileeplearning and
I need someone to end it... I’m incapable of doing so.pic.twitter.com/zM8wkSsksU
1 reply 0 retweets 4 likes -
Replying to @tyrell_turing @AdamMarblestone and0 replies 0 retweets 3 likes
End of conversation
New conversation -
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.