Medijski sadržaj
- Tweetovi
- Tweetovi i odgovori
- Medijski sadržaj, trenutna stranica.
-
In “Artificial Intelligence, Values and Alignment” DeepMind’s
@IasonGabriel explores approaches to aligning AI with a wide range of human values: https://deepmind.com/research/publications/Artificial-Intelligence-Values-and-Alignment …pic.twitter.com/Zo81PSpwyF
-
Given the smoothness of videos, can we learn models more efficiently than with
#backprop? We present Sideways - a step towards a high-throughput, approximate backprop that considers the one-way direction of time and pipelines forward and backward passes. https://arxiv.org/pdf/2001.06232.pdf …pic.twitter.com/evbwULE0s2 -
How can we predict and control the collective behaviour of artificial agents? Classical game theory isn't much help when there are >2 agents. In our
@iclr_conf paper, we find markets impose useful structure on interactions between gradient-based learners: https://arxiv.org/abs/2001.04678 pic.twitter.com/IeLMcb9f2z
-
More exciting
@Nature news today: an example of how AI and neuroscience continue to propel each other forward. (1/2)pic.twitter.com/ba6ZWjF95o
Prikaži ovu nit -
Proteins are the building blocks of biology. They start off as a string of amino acids that fold into intricate 3D structures. Knowing the 3D structure helps us understand their function, but predicting such structures is an unsolved question in science. 2/4pic.twitter.com/1meRwkYKFI
Prikaži ovu nit -
If you’re looking for something to listen to this week, try DeepMind: The podcast. Hear from
@jhamrick,@vkrakovna@OriolVinyalsML,@wsisaac and many others from our talented teams.
https://apple.co/393Kufo
https://spoti.fi/36RXN0t
#dmpodcastpic.twitter.com/vi5lHGlMkj
-
[2/2] Find out more about Google’s Project Euphonia and Tim’s story in the new
@YouTube Originals learning series#AgeOfAI, out today:https://www.youtube.com/watch?v=V5aZjsWM2wo …Prikaži ovu nit -
After being named as new and noteworthy by
@applepodcasts, we’re proud that DeepMind: The podcast with@FryRsquared is also one of the top shows in both the Science and Technology categories.
and subscribe here:
http://apple.co/2KZXx7B pic.twitter.com/H9YTBUMvuE
-
DeepInsight is a decoding framework for discovering and characterising the neural correlates of behaviour and stimuli in unprocessed biological data: http://biorxiv.org/content/10.1101/871848v1 …pic.twitter.com/K6goibHlha
Prikaži ovu nit -
What does it mean to understand language? We argue that human-like understanding requires complementary memory systems and rich representations of situations. A roadmap for extending ML models toward human-level language understanding: https://arxiv.org/abs/1912.05877 pic.twitter.com/eKBOekfmgj
Prikaži ovu nit -
We’re in the final stretch of
#NeurIPS2019! Thanks for so many engaging discussions so far this week. Today and tomorrow, we’ll be wrapping up by co-organising the following workshops:pic.twitter.com/uB7qTVNgfQ
-
Read more in our recent blog post: https://deepmind.com/blog/article/learning-human-objectives-by-evaluating-hypothetical-behaviours …pic.twitter.com/cgHk96zhJP
Prikaži ovu nit -
We present ReQueST: a method for training RL agents from human feedback in the presence of unknown unsafe states. By
@sidgreddy,@ancadianadragan,@svlevine,@ShaneLegg,@janleike Paper: https://arxiv.org/abs/1912.05652 Code: https://github.com/rddy/ReQueST pic.twitter.com/qM8GSaMcr2
Prikaži ovu nit -
Good morning
#NeurIPS2019! See below for today’s lineup of posters & presentations:pic.twitter.com/FMA6K2X5yy
-
Training data is often collected through a biased process. Models trained on such data are inherently biased. We demonstrate how adversarial training through disentangled representations can reduce the effect of spurious correlations present in datasets: http://arxiv.org/abs/1912.03192 pic.twitter.com/YjJpnY1E8k
-
We're looking forward to today's sessions at
#NeurIPS2019 - see below for our schedule of presentations:pic.twitter.com/hwNGNT8ZmY
Prikaži ovu nit -
It's been great to meet so many of you at
#NeurIPS2019 so far! For those curious to learn more about how we think about AI and our approach to science, check out@DemisHassabis in The Economist for “The World in 2020”: https://worldin.economist.com/article/17385/edition2020demis-hassabis-predicts-ai-will-supercharge-science …#WorldIn20 Today's schedule:pic.twitter.com/0sszAGAyeT
Prikaži ovu nit -
#NeurIPS2019 - the 33rd Conference on Neural Information Processing Systems - is now under way! We’re looking forward to this week’s tutorials, workshops, and sessions. Come say hello to the team @ our booth. We'll post schedules and updates here throughout the week!pic.twitter.com/o5FgNMP0MY
Prikaži ovu nit -
We introduce LOGAN, a game-theory motivated algorithm, which improves the state-of-the-art in GAN image generation by over 30% measured in FID: https://arxiv.org/abs/1912.00953 Here are samples showing higher diversity:pic.twitter.com/GkdRofrYRt
-
If you’re thinking about doing a Masters in Computer Science, listen to
@shaqzle's story and find out if a#DeepMindScholarship is the right fit for you: http://deepmind.com/scholars https://youtu.be/koEWIEHTopo
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.