Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @jacobmbuckman
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @jacobmbuckman
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Jacob Buckman proslijedio/la je Tweet
The whole thread on BNNs and blog post by
@jacobmbuckman and@carlesgelada reminded me of the "First, you rob a bank..." characterization by Yasser Abu Mostafa https://www.youtube.com/watch?v=ihLwJPHkMRY&t=2440 … Apologies to my Bayesian friends who may find it unfair.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jacob Buckman proslijedio/la je Tweet
New blog post! This time I'm looking at recent advances in memory-efficient training and where that might lead.http://mitchgordon.me/machine/learning/2020/01/13/do-we-really-need-model-compression.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The old version will remain accessible online for posterity, but I've removed it from my blog's index, and added a link to the updated version of the post.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We've updated this blog post in response to community discussion & feedback:https://twitter.com/jacobmbuckman/status/1220012977727987712 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Updated blog post with
@carlesgelada -- "Bayesian Neural Networks Need Not Concentrate": https://jacobbuckman.com/2020-01-22-bayesian-neural-networks-need-not-concentrate/ … Thanks to all for the discussion & feedback. This improved version of the blog post hopefully explains the core claims more clearly, while being less polarizing.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If a result relevant to our discussion is included in some prior work, by all means reference it! But blanket dismissal of all ideas that come from people who haven't already completed your exact personal "required reading" is a disturbingly elitist attitude.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It's frustrating when people refuse to have idea-level discussions on the grounds that "since you missed this 1 reference, you aren't worth talking to." Feels very patronizing and anti-good-discourse.https://twitter.com/carlesgelada/status/1219386058972049415 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We'll update the blog post to include this new evidence. If anyone is interested in empirically investigating these questions about BNN priors in more detail, feel free to reach out and/or pull my repo!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Overall, there does seem to be a significant difference between the prior probability of just clean data, and clean + corrupted! This is evidence that BNN priors are *not* entirely generalization-agnostic. My hypothesis was wrong!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Results are in! Averaged over 3 trials: unregularized: logp(clean) = -1654049 logp(clean+corrupted) = -1654101 with .01 reg towards prior: logp(clean) = -1654024 logp(clean+corrupted) = -1654066 code: https://github.com/jbuckman/ga-prior-or-nah …https://twitter.com/jacobmbuckman/status/1219111097330032640 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is a more nuanced elaboration on Carles's controversial thread from a few weeks ago:https://twitter.com/carlesgelada/status/1208618401729568768 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New blog post with
@carlesgelada -- "A Sober Look at Bayesian Neural Networks": https://jacobbuckman.com/2020-01-17-a-sober-look-at-bayesian-neural-networks/ … Without a good prior, Bayesian uncertainties are meaningless. We argue that BNN priors are likely quite poor, and concretely characterize one specific failure mode.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jacob Buckman proslijedio/la je Tweet
I propose a grand challenge for dextrous robotic manipulation: cook eggs in all the ways shown in this videohttps://www.youtube.com/watch?v=BW1x6F63F80 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Is causal inference the same thing as "batch RL" (learning from data without interacting)? Or is there more to it?
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
in case anyone was wondering what it's like to argue with
@carlesgelada irlhttps://twitter.com/carlesgelada/status/1208673067536396290 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Highly persuasive rant. Any Bayesians out there willing to defend the reverend's honor?https://twitter.com/carlesgelada/status/1208618401729568768 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jacob Buckman proslijedio/la je Tweet
First airplane with no moving parts: no turbines, propellers, nor jets. Uses electroaerodynamic propulsion, where 40k volts generate ions moving from a larger electrode to a smaller one, colliding with air molecules on the way to produce "ionic wind". https://www.nature.com/articles/s41586-018-0707-9 …pic.twitter.com/tujjriAla2
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jacob Buckman proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.