-
মানুষজন সবকটি দেখুন
@laurent_dinh Deep learning mercenary. Research scientist
@GoogleAI MTL.@MILAmontreal PhD graduate. Tweets were not peer reviewed. -
... Yann Lecun on Learning World Models with Self-Supervised Learning (and his now famous fast car down the cliff .gif)
#icml2018 pic.twitter.com/g1MTwuPARX
এই থ্রেডটি দেখান -
Our poster for the "Prediction and Generative Modeling in Reinforcement Learning" workshop in B2
#ICML2018@him_sahni@yscrcrpic.twitter.com/0NoQs4k0Lf
-
Pics from our
#ICML2018 Workshop on Theoretical Foundations & Applications of Deep Generative Models https://sites.google.com/view/tadgm Huge thanks to@ZhitingHu who put a lot of work into organizing & thanks to speakers for their amazing talks! with Zhiting,@andrewgwils@rsalakhu & Ericpic.twitter.com/Bkj5ZEM6SP
-
.
@alicecoucke and I will be presenting our work@snips on building a private, embedded Spoken Language Understanding system in the Privacy in Machine Learning and Artificial Intelligence workshop at#ICML2018. We'll be in room C2, for the poster session from 11.10am!#PiMLAI18pic.twitter.com/d2dFmMLmVg
-
Rich Sutton at Lifelong Learning workshop (paraphrase): I don’t like standardized testbeds. They reduce science to “my number is better than yours”. We should come up with new ideas and hypotheses and design experiments to test those hypotheses and get new insights.
#ICML2018 pic.twitter.com/AIAnZivb3B
-
-
Holy. Shit. Expressive, interesting, and lengthy piano music generations. I genuinely got goosebumps listening to these. As far as I'm concerned, this is a huge step forward for creative ML. Cheers Anna Huang. Paper: https://docs.google.com/viewer?a=v&pid=sites&srcid=ZGVmYXVsdGRvbWFpbnxmYWltbXVzaWMyMDE4fGd4Ojc5YWM3ZmJkNDBhMzJkNzg …
#icml2018 pic.twitter.com/WjECu2h3Plএই থ্রেডটি দেখান -
Come see us today at the
#ICML2018 WCB presenting "Learning to rank for censored survival data" https://arxiv.org/abs/1806.01984 (work from@MILAMontreal)pic.twitter.com/WaYh3n3ee6
-
Deep reflection by Cynthia Rudin on recent algorithms on for interpretable ML at
#icml2018 Fairness, interpretability and explanability workshop - The definition of interpretability is context specific - it's harder to get an interpretable model than to get an accurate model pic.twitter.com/3Dbza1Et3r
-
Slides of my talk at
#ICML2018 on reproducible#MachineLearning workshop https://www.slideshare.net/agramfort/icml-2018-reproducible-machine-learning-a-gramfort … https://mltrain.cc/events/enabling-reproducibility-in-machine-learning-mltrainrml-icml-2018/ …#RML2018@scikit_learn#opensource#opensciencepic.twitter.com/CU22oMgsoS
-
Really nice talk today at
#ICML2018 highlighting, amongst other things, the important historical contributions from cognitive science and psychology to machine learning and AI by Josh Tenenbaum. pic.twitter.com/PngcLb5eGK
-
-
Come see my talk on Born Again Neural Networks at 5:40 room Victoria , and from 6:30 poster # 106 with co-authors
@zacharylipton Michael Tschannen Laurent Itti and@AnimaAnandkumar https://arxiv.org/abs/1805.04770#ICML2018 pic.twitter.com/61owjBjziF
-
“Building machines that learn and think like people” fine talk by
@joshtenenbaum#ICML2018 pic.twitter.com/bPtkU1buVC
এই থ্রেডটি দেখান -
Cool work by
@AlekhAgarwal@hannawallach John Langford and others presented at#ICML2018 A fairness wrapper for black-box classifiers which works based on sample reweighting at training time and does not use sensitive attributes at test time. https://github.com/Microsoft/fairlearn …pic.twitter.com/G9xefBuwZQ
-
I will talk about our new work on "Bayesian deep learning using weight-perturbation in Adam" at
#icml2018 in "Deep Learning (Bayesian) 2" session at 4:50pm in room A4. Paper here https://arxiv.org/abs/1806.04854 Slides here https://goo.gl/ouZRkM Code here https://goo.gl/5uHDSH 1/6pic.twitter.com/dgXDfW3Z21
এই থ্রেডটি দেখান -
Please share: The newly created "Foundations team" of
@DeepMindAI have openings for research scientists with strong theoretical background, and an unstoppable interest in pushing the boundaries of AI and machine learning. PM me if you are interested.#ICML2018 -
”AI algorithms will be measured by the amount of intelligence they provide per kilowatthour.” Max Welling
#ICML2018 pic.twitter.com/AZeZvI1TFG
-
At
#icml2018 in Stockholm this week! Come check our poster on improved uncertainty estimation for Bayesian models and deep neural networks on Thursday. pic.twitter.com/bcaOeyeMRm
এই থ্রেডটি দেখান -
#ICML2018 NOISIN by@adjiboussodieng etal Great work on an explicit regularizer that imposes a robustness constraint on the hidden units of the RNN +how it improves the generalization capabilities of LSTM & do-LSTM on a language modeling benchmark. Click https://goo.gl/1rrKAQ pic.twitter.com/bsO7Poi3NZ
লোড হতে বেশ কিছুক্ষণ সময় নিচ্ছে।
টুইটার তার ক্ষমতার বাইরে চলে গেছে বা কোনো সাময়িক সমস্যার সম্মুখীন হয়েছে আবার চেষ্টা করুন বা আরও তথ্যের জন্য টুইটারের স্থিতি দেখুন।