Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @LakeBrenden
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @LakeBrenden
-
Brenden Lake proslijedio/la je Tweet
Well, for Spring 2020 there are 90 registered students in the NYU Computational Cognitive Modeling graduate class with
@LakeBrenden and a waitlist of 42.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Brenden Lake proslijedio/la je Tweet
Facebook's AI Residency program, which gives residents 12 months of practical experience in AI working with leading researchers, is accepting applications until January 31st! Current residents Diana and Eric discuss their experience in this Q&A: https://ai.facebook.com/blog/qa-with-facebook-ai-residents-eric-mintun-and-diana-gonz%C3%A1lez/ …pic.twitter.com/wiNe0v9nA7
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
A disturbing use of facial recognition tech from a start-up in lower Manhattan. My recommendation: replace your profile photos with adversarial imageshttps://www.nytimes.com/2020/01/18/technology/clearview-privacy-facial-recognition.html?action=click&module=Top%20Stories&pgtype=Homepage …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The source code for meta seq2seq learning is now available through
@facebookai. You can reproduce the experiments from my#NeurIPS2019 paper, or run memory-based meta learning on other seq2seq problems. https://github.com/facebookresearch/meta_seq2seq …https://twitter.com/LakeBrenden/status/1205015995787595776 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"The number of tech jobs in New York City has surged 80 percent in the past decade, to 142,600, from 79,400 in 2009"https://www.nytimes.com/2020/01/05/nyregion/nyc-tech-facebook-amazon-google.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Frostbite scores in our paper were Josh Tenenbaum and
@TomerUllman. My score, in fact, remains unpublished :)https://twitter.com/nicholdav/status/1212937908740612096 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Brenden Lake proslijedio/la je Tweet
Submissions for our workshop on "Bridging AI and Cognitive Science" at
#ICLR2020 are now open! Submit your recent work, work in progress, or controversial opinions at the intersection of AI and cognitive science. https://baicsworkshop.github.io/ https://twitter.com/jhamrick/status/1206591213522042881 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Brenden Lake proslijedio/la je Tweet
Bayesian methods are *especially* compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. This difference will be greatest for underspecified models like DNNs. 1/18https://twitter.com/carlesgelada/status/1208618401729568768 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Brenden Lake proslijedio/la je Tweet
Our theme issue is out: If you are interested in compositionality from formal, computational, or neurophysiological/neurobiological perspectives with a mechanistic bent, eat your heart out! It was an honour to edit this together with the inimitable Giosuè Baggio
@giosuebaggio.https://twitter.com/RSocPublishing/status/1206552151784333322 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"Systematic generalization" and "compositionality" were buzzwords at
#NeurIPS2019. At the meta-learning workshop, I discussed compositionality in human language and thought, and how understanding it would inform machine intelligence. Video begins 26:35https://slideslive.com/38921885Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I hear “It’s all just experience” used to justify training algorithms for thousands of years worth of experience (often on just one game or task). But let’s not confuse this with human-like learning, and let's not dismiss fundamental questions about the origins of knowledge!(2/2)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It’s misleading to lump together nature and nurture as just “experience.” The extent to which capabilities are built-in vs. learned is foundational in cognitive science and cognitive development, because it suggests different representations, architectures, algorithms, etc. (1/2)https://twitter.com/karpathy/status/1206064174129930240 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Maxwell Nye talking about learning compositional rules via neural program synthesis, in
#neurips19 context and compositionality workshop https://context-composition.github.io pic.twitter.com/jfURigDL2s
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Brenden Lake proslijedio/la je Tweet
Our workshop on Context & Composition in Biological and Artificial Neural Systems
#NeurIPS2019 just started! Come hear perspectives from folks like@GaryMarcus &@ev_fedorenko https://context-composition.github.io/ pic.twitter.com/gP0ReSo46f
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I'm speaking on "Compositional generalization in minds and machines" at 5 today in the
#NeurIPS2019 meta learning workshop (West Ballroom B). Will cover SCAN benchmark, human experiments, and compositional generalization through "meta seq2seq learning" http://metalearning.ml/2019/Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Here's a link to the progress report: Lake, B. M., Salakhutdinov, R., and Tenenbaum, J. B. (2019). The Omniglot challenge: a 3-year progress report. Current Opinion in Behavioral Sciences, 29, 97-104.https://www.sciencedirect.com/science/article/pii/S2352154619300051 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Our "progress report" on the Omniglot Challenge was featured in this year's AI index report: "Achieving human-level concept learning will require learning richer representations from less data, and reconfiguring these representations to tackle new tasks.” (see pgs 64 and 223)https://twitter.com/StanfordHAI/status/1205140347204055040 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The best part of conferences is catching up with friends like these two. We should dig up a picture from the 2010 machine learning summer school in Sardinia, where we really got to know each otherhttps://twitter.com/celestekidd/status/1205116939791519744 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Neural nets struggle with systematic generalizaton, but can be improved through "meta seq2seq learning": training on many seq2seq problems to acquire the compositional skills needed for solving new problems. Come by
#NeurIPS2019 poster 178 Thu. at 10:45 https://arxiv.org/abs/1906.05381 pic.twitter.com/GyUuCr6f0B
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Brenden Lake proslijedio/la je Tweet
Mini thread: If you haven't already
@FChollet's beautiful & insightful paper on intelligence & AI, you should. An elegant distillation of where we are now, & an intriguing proposal for how to make progress. https://arxiv.org/abs/1911.01547Prikaži ovu nitHvala. 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.