Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @liyuajia
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @liyuajia
-
Yujia Li proslijedio/la je Tweet
The "Deep Learning Toolbox" has greatly expanded in the last decade thanks to our wonderful research community. Also, important progress has been made to make our community more inclusive and less toxic. Still, there's LOTS to do, and I plan to keep focusing on advancing both.pic.twitter.com/C5r4wDGSN9
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Graph representation learning is the most popular workshop of the day at
#NeurIPS2019 . Amazing how far the field has advanced. I did not imagine so many people would get into this when I started working on graph neural nets back in 2015 during an internship. Time flies...pic.twitter.com/H8LM0BMvK4
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We were exploring ideas on using learning to help solve SAT. But realized this really simple algorithm (a slight variation of unit propagation) is hard to beat, at least for random SAT instances. https://arxiv.org/abs/1912.05906 pic.twitter.com/pMhHfkGxHB
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Our NeurIPS paper on learning to explore graph structured spaces uses graph neural networks to learn to explore (visit as many different nodes as possible) efficiently. We got great results on program testing (covering all code branches) and even testing Android apps!https://twitter.com/DeepMind/status/1190221617898643457 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yujia Li proslijedio/la je Tweet
Our new
@nature paper: AlphaStar is the first learning system to reach the top tier of a major esport without any game restrictions, achieving Grandmaster status in StarCraft II. Researchers have been working on the StarCraft series for over 15 years. https://deepmind.com/blog/article/AlphaStar-Grandmaster-level-in-StarCraft-II-using-multi-agent-reinforcement-learning …pic.twitter.com/ohOotyrhB0
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New paper at
#NeurIPS2019 on generative models of graphs. We explored many quality-efficiency trade-offs in this work and came up with a new model that gets good graph generation quality with much better efficiency. Paper: https://arxiv.org/abs/1910.00760 Code: https://github.com/lrjconan/GRAN https://twitter.com/lrjconan/status/1179573683238649857 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
An example implementation of our graph matching networks is on github now! https://github.com/deepmind/deepmind-research/tree/master/graph_matching_networks … The code is for our ICML paper: https://arxiv.org/abs/1904.12787 . The release includes a reference implementation, a simple training loop, a synthetic task and some visualization tools.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We just released a dataset of synthetic computation graphs https://github.com/deepmind/deepmind-research/tree/master/regal … used in our REGAL paper https://arxiv.org/abs/1905.02494 . A learned GNN policy improves running time and memory consumption of TF and XLA graphs. Training on synthetic graphs generalizes to real graphs!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yujia Li proslijedio/la je Tweet
Sparse graph neural networks can be trained efficiently on dense hardware (TPU), and large-batch training works: instead of a day on 1 GPU, a network trains in 13 minutes on a 512-core TPU. Work with
@bvanmerrienboer, @subho87,@liyuajia,@numbercrunching: https://arxiv.org/abs/1906.11786Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We reduced the training time of a sparse graph neural net from 1 day to 13 mins (!) on TPU with large batch training. Key is identifying band-diagonal structure in the adjacency matrix. Work with
@matejbalog@bvanmerrienboer @subho87@numbercrunching Paper https://arxiv.org/abs/1906.11786 pic.twitter.com/2NiaDCVlIa
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
CVPR thought I was an outstanding reviewer, surprise! No email or anything, only realized when someone else told me. Thought people would gradually stop reviewing for conferences as they get more senior, but wrong - ACs must be lucky to have Andrew Zisserman as a reviewer!https://twitter.com/cvpr2019/status/1137626416550252544 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yujia Li proslijedio/la je Tweet
Interested in discovering latent hierarchical structure and option discovery in RL? Come visit our talk/poster on CompILE at
@icmlconf tomorrow! w/@liyuajia@egrefen@pushmeet@PeterWBattaglia et al. Talk: Wed. 4:40-5:00pm, Hall B (Poster #56) Paper: https://arxiv.org/abs/1812.01483 pic.twitter.com/pz4pjtIC8W
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yujia Li proslijedio/la je Tweet
Accepted papers at the
@icmlconf Workshop on Learning and Reasoning with Graph-Structured Data are now available on the workshop website: Papers: https://graphreason.github.io/papers.html Schedule: https://graphreason.github.io/schedule.html pic.twitter.com/Y1v1snR6Gv
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yujia Li proslijedio/la je Tweet
The camera-ready version of our CompILE
@icmlconf paper is out! Differentiable sequence segmentation for option discovery in RL — w/@liyuajia@egrefen@pushmeet@PeterWBattaglia et al. Paper: https://arxiv.org/abs/1812.01483 Code: https://github.com/tkipf/compile pic.twitter.com/4RnGTGlEhr
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
And we can do all these with weak or even no supervision!https://twitter.com/thomaskipf/status/1128629254445465600 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Graph neural net + REINFORCE + genetic algorithm = 3% or more memory reduction for your computation graph. Learned model can generalize to unseen graphs 10x larger and with unseen op types. Runtime can also be optimized. Paper: https://arxiv.org/abs/1905.02494 pic.twitter.com/WXIm3T1C4Z
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yujia Li proslijedio/la je Tweet
Our latest work on neural network models for reasoning about similarity between graph structured objects, with implications for a broad spectrum of applications: https://arxiv.org/abs/1904.12787 By
@liyuajia,@calbeargu, Thomas Dullien,@OriolVinyalsML and@pushmeetpic.twitter.com/KbHzQdjh5BHvala. 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.