|
Dileep George
@
dileeplearning
San Francisco, CA
|
|
Founder at Vicarious AI (@vicariousai vicarious.com). Previously Founder and CTO at Numenta. Triply EE (BTech IIT-Mumbai, MS&PhD Stanford)
|
|
|
1.187
Tweetovi
|
359
Pratim
|
2.184
Osobe koje vas prate
|
| Tweetovi |
|
Dileep George
@dileeplearning
|
5 h |
|
Forget the amoeba, human free will is still being debated :)
|
||
|
|
||
|
Dileep George
@dileeplearning
|
5 h |
|
to be considered agency, it should be able to stop doing that at will when the yeast cell is present. Can it? Or is it a hardwired stimulus-response mapping that we are anthropomorphizing?
|
||
|
|
||
| Dileep George proslijedio/la je tweet | ||
|
Brad Wyble
@bradpwyble
|
3. velj |
|
Insanely weird bistable photo. Is this a dog or a weird looking goat?
(not sure where the photo is from, can't provide credit) pic.twitter.com/7wlSpC8Xph
|
||
|
|
||
|
Dileep George
@dileeplearning
|
3. velj |
|
Thank you!
|
||
|
|
||
|
Dileep George
@dileeplearning
|
2. velj |
|
no, it is just an accurate depiction of my drawing disability.. :)
|
||
|
|
||
|
Dileep George
@dileeplearning
|
2. velj |
|
thanks for making it!
|
||
|
|
||
| Dileep George proslijedio/la je tweet | ||
|
Ahmed Maher
@iAhmedMaher
|
2. velj |
|
If u ever wondered about the inner workings of @vicariousai's RCNs, I just published an article on it: link.medium.com/FLaUqgpPK3
#ArtificialIntelligence #MachineLearning
|
||
|
|
||
|
Dileep George
@dileeplearning
|
2. velj |
|
This blog on RCN model is just excellent with amazing visuals! I highly recommend it, especially if you are interested in generative visual models based on the visual cortex. twitter.com/iAhmedMaher/st…
|
||
|
|
||
|
Dileep George
@dileeplearning
|
2. velj |
|
#AGIcomics take on the trolley problem. pic.twitter.com/PzXKDh9xLb
|
||
|
|
||
|
Dileep George
@dileeplearning
|
30. sij |
|
Really nice! For your module on generative models, I would like to suggest our RCN paper, which has exactly this kind of shape-object factorization and is an example of a neuroscience inspired predictive-coding model that works in practice. science.sciencemag.org/content/358/63… pic.twitter.com/CViGu8Tuzv
|
||
|
|
||
|
Dileep George
@dileeplearning
|
29. sij |
|
yes, I think it is an interesting problem to work on. We dabbled on that problem some time ago, but haven't really pursued it in a while.... vicarious.com/2017/08/07/gen…
|
||
|
|
||
|
Dileep George
@dileeplearning
|
29. sij |
|
reachability analysis a static setting is easy via message-passing. Just propagate forward from the current state until you hit the target or exceed the graph diameter. Sokoban settings can be arbitrarily hard because you can move blocks out of the way etc.
|
||
|
|
||
| Dileep George proslijedio/la je tweet | ||
|
Dileep George
@dileeplearning
|
29. sij |
|
Nice video. This is exactly the innateness that is used in our paper "Different clones for different contexts" (biorxiv.org/content/10.110…) and in our cognitive maps paper that learns spatial layout from from ordinal sequential info biorxiv.org/content/10.110…
|
||
|
|
||
|
Dileep George
@dileeplearning
|
29. sij |
|
Nice video. This is exactly the innateness that is used in our paper "Different clones for different contexts" (biorxiv.org/content/10.110…) and in our cognitive maps paper that learns spatial layout from from ordinal sequential info biorxiv.org/content/10.110…
|
||
|
|
||
|
Dileep George
@dileeplearning
|
28. sij |
|
Amelia Bedelia?
|
||
|
|
||
|
Dileep George
@dileeplearning
|
28. sij |
|
also message-passing for inspired by the interactive activation model fwiw
|
||
|
|
||
|
Dileep George
@dileeplearning
|
28. sij |
|
We do it in our paper using message-passing. It is approximate, and there are no theoretical guarantees, but works really well in the settings we have tried. Also it is very fast.
|
||
|
|
||
|
Dileep George
@dileeplearning
|
28. sij |
|
it buys an a mechanism to do "dynamic inference" in an economic way. By dynamic I mean it is not amortized inference that requires exposure to all the different compositions during training.
|
||
|
|
||
|
Dileep George
@dileeplearning
|
28. sij |
|
"reality of the letters", doesn't really exist :). I can show you lots of characters that are created purely via subjective contours.
|
||
|
|
||
|
Dileep George
@dileeplearning
|
28. sij |
|
thanks! :).
I think I understand what you mean. Resolving all that context might be equivalent to abductive inference though, right?
|
||
|
|
||