Interested in AI for games, games for AI, game design, serious games, procedural content generation, player modeling, and similar?
— Julian Togelius (@togelius) August 21, 2019
All of the papers from the currently ongoing IEEE Conference on Games are available for free athttps://t.co/hMyghz9pmv@cog2019ieee #CoG2019
Presenting LXMERT at @EMNLP2019 --> https://t.co/T9SeONSlFO (prnc. 'leksmert'). Top3 in GQA & VQA challenges (May2019), Rank1 in VizWiz, & v.strong generalzn to NLVR2 (22% abs jump)! Awesome effort by @HaoTan5!
— Mohit Bansal (@mohitban47) August 21, 2019
CODE+MODELS all public: https://t.co/JWbjEWbhXS; pls use+share! 1/2 pic.twitter.com/WvxRirYGoB
This new tool from for systematic error analysis from @uwdata looks like it will be really useful!
— Christopher Manning (@chrmanning) August 20, 2019
(I fear the common standard of 100 sampled errors in QA papers is my fault – we intended to do 200, but I never got around to doing my half….) https://t.co/0Py7IpOFRD
GPT-2 6-month follow-up: we're releasing the 774M parameter model, an open-source legal doc organizations can use to form model-sharing partnerships, and a technical report about our experience coordinating to form new publication norms: https://t.co/wnLwmRt9jT
— OpenAI (@OpenAI) August 20, 2019
Nice blog post about a series of optimizations to reduce training time of a CIFAR10 image model. Many of these options are likely applicable to lots of different kinds of models. Nice work, @dcpage3! https://t.co/jmS23Xtnyt
— Jeff Dean (@JeffDean) August 19, 2019
Nice manuscript summarizing and evaluating current AutoML methods: "Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools" https://t.co/iA6OfFdQTN
— Sebastian Raschka (@rasbt) August 17, 2019
@jeremyphoward Could I introduce you to Novograd? https://t.co/1U8psyl3Io Also consistently better results than SGD/Adam with half the memory footprint of Adam.
— Ryan Leary (@ryaneleary) August 15, 2019
"New State of the Art AI Optimizer: Rectified Adam (RAdam). Improve your AI accuracy instantly versus Adam, & why it works"
— Jeremy Howard (@jeremyphoward) August 15, 2019
It's been a long time since we've seen a new optimizer reliably beat the old favorites; this looks like a very encouraging approach!https://t.co/1MZmTbmFjn
Arguing that large-batch doesn't generalize well: https://t.co/DCFmkK5yWu
— Ferenc Huszár🇪🇺 (@fhuszar) August 15, 2019
Arguing that full batch GD does in fact generalize:https://t.co/nUXQJEu2LV (Table 1)
A nice blog post explaining recent progress in NLP and translation and some Facebook AI's contributions.
— Yann LeCun (@ylecun) August 14, 2019
BERT, RoBERTa, backtranslation, GLUE, SuperGLUE, WMT explained.... https://t.co/sFl6VxdWx5
We’re detailing our recent #NLP breakthroughs: surpassed existing benchmarks on key tasks; led the #WMT2019 competition ranking higher than humans, per organizers; & partnered with @nyuniversity, @uw & @deepmindAI on SuperGLUE, a new harder benchmark: https://t.co/h2rT3WKBpI pic.twitter.com/yQ5feVKZDt
— Facebook AI (@facebookai) August 14, 2019
A Survey on Cross-lingual Word Embedding Models has been published in @JAIR_Editor. If you're interested in cross-lingual learning, then this should be a good starting point. It covers the history and points to interesting future directions.https://t.co/BXP1GuvQCl pic.twitter.com/46QkgZYxJd
— Sebastian Ruder (@seb_ruder) August 14, 2019
