| Tweetovi |
|
Frans Zdyb
@FZdyb
|
23. sij |
|
en.m.wikipedia.org/wiki/Witold_Pi…
Srsly, if they'd make a movie about this guy it would make James Bond look realistic in comparison. twitter.com/DanielJHannan/…
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
14. sij |
|
The unique feature that cpu's and brains have in common is that they accept arbitrary data and programs as input and reliably produce the correct output. But brains are even more unique because they program themselves (to some extent).
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
14. sij |
|
I like the post, but I think it's incomplete. Your argument says brains are physical systems, and all physical systems can be simulated by a Turing machine. But some systems are better understood as computers than others (a cpu vs a piece of quartz). (1/2)
|
||
|
|
||
| Frans Zdyb proslijedio/la je tweet | ||
|
David Chapman
@Meaningness
|
9. sij |
|
.@slatestarcodex is an extraordinary, massive, persistent force of nature, like Jupiter’s Great Red Spot or something.
Read his decade in review and be gobsmacked: slatestarcodex.com/2020/01/08/wha…
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
28. pro |
|
No metal in the responses?
Tesseract - Altered State
Animals as Leaders - Joy of Motion
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
5. stu |
|
Information as a concept only makes sense when one physical system encodes it s.t. another can decode it. If you consider the entire universe, it's impossible to specify a decoder, and the question dissolves.
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
25. lis |
|
Douglas Hofstadter wrote an essay about Google Translate that explains it theatlantic.com/technology/arc…
|
||
|
|
||
| Frans Zdyb proslijedio/la je tweet | ||
|
Rohin Shah
@rohinmshah
|
21. lis |
|
Excited to share our work: collaboration requires understanding! In Overcooked, self-play doesn't gel with humans: it expects them to play like itself. (1/4)
Demo: humancompatibleai.github.io/overcooked-dem…
Blog: bair.berkeley.edu/blog/2019/10/2…
Paper: arxiv.org/abs/1910.05789
Code: github.com/HumanCompatibl… pic.twitter.com/lqbzeTwoqr
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
14. lis |
|
Alright, I'm pretty sure I'm not getting your point, maybe let's just leave it at that :)
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
14. lis |
|
Scientific realism is bad philosophy?
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
12. lis |
|
Why do we still see eye floaters though? Seems like an easy thing to remove in post processing.
|
||
|
|
||
| Frans Zdyb proslijedio/la je tweet | ||
|
Future of Life
@FLIxrisk
|
9. lis |
|
We've interviewed Stuart about his new book here: futureoflife.org/2019/10/08/ai-…
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
4. lis |
|
On second thought, maybe we assume that the posterior is low-entropy enough that MC-expectations over it are that much more robust than with the prior?
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
4. lis |
|
I'm thinking one could take an approach for ML and adapt it (e.g. arxiv.org/abs/1511.02543).
I love the idea of Soss.jl, btw. It looks like we're interested in many of the same things! I've been experimenting with ASTs and programmatic transformations of Pyro models for example.
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
3. lis |
|
I mean, ML is integrating the product of likelihood and prior over all parameters; PP is integrating the product of likelihood and posterior over the same space. There are countless papers on approximating ML in various ways, but the standard prescription for PP is just sampling.
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
3. lis |
|
Why do people estimate the predictive posterior by regular sampling when it's exactly as hard as computing marginal likelihood? Please tell me I'm missing something obvious.
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
27. ruj |
|
Great to meet ML people in the industry :) so long and thanks for all the swag! twitter.com/SAPDanmark/sta…
|
||
|
|
||
| Frans Zdyb proslijedio/la je tweet | ||
|
Steven Strogatz
@stevenstrogatz
|
25. ruj |
|
"MIT Mathlets" = mathlets.org/mathlets/
These are terrifically visual, interactive applets for learning about differential equations and related parts of math. Very intuitive and easy to use, and beautifully designed by Hubert Hohn, an artist who took my chaos course at MIT
|
||
|
|
||
|
Frans Zdyb
@FZdyb
|
15. kol |
|
Surfing Uncertainty
The Moral Animal
Mastering the Core Teachings of the Buddha
(1) The contents of consciousness are mental fabrications, (2) whose function is not to reflect reality, but be adaptive. (3) If you focus really hard on those contents, you'll see it for yourself.
|
||
|
|
||
| Frans Zdyb proslijedio/la je tweet | ||
|
Max Welling
@wellingmax
|
20. tra |
|
I wrote this response to Rich Sutton's "The Bitter Lesson"
staff.fnwi.uva.nl/m.welling/wp-c…
|
||
|
|
||