No, you’re not getting my point... I’m not saying representations or learning can be fully decoupled, nor telling neuroscientists (of which I am one) just tell us how the brain does backprop.
-
-
Replying to @tyrell_turing @dileeplearning and
I’m saying: neuroscience needs to start thinking in terms of cost functions and optimization, rather than tuning curves and Hebbian plasticity.
1 reply 0 retweets 7 likes -
Replying to @tyrell_turing @dileeplearning and
These both seem like good research programs at our present state of understanding. 1) If the signals in the world have a particular (1/14)
1 reply 0 retweets 3 likes -
Replying to @AdamMarblestone @tyrell_turing and
structure, it may be possible to use probabilistic graphical models, with pre-built formats reflecting that structure, to learn to (2/14)
1 reply 0 retweets 3 likes -
Replying to @AdamMarblestone @tyrell_turing and
model those world signals, and it may be possible to so more efficiently than one could by backprop from even a well-chosen cost (3/14)
2 replies 0 retweets 5 likes -
Replying to @AdamMarblestone @tyrell_turing and
function. It would be very interesting if the brain did something like that and if so, it would be reflected in the (4/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
micro-circuitry. 2) Figuring out a) if and b) how the brain implements a learning algorithm as powerful and general as (5/14)
1 reply 0 retweets 4 likes -
Replying to @AdamMarblestone @tyrell_turing and
backprop/gradient descent, and if so what cost functions it optimizes, is very important regardless of whether a) turns out in the (6/14)
1 reply 0 retweets 5 likes -
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
ground-truth cortical microcircuit and brain macro-circuit data, and we need to better curate the literature to have good answers (9/14)
-
-
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 - 7 more replies
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.