News & trends in the Last 48 hours
News & trends in the Last 48 hours
In the Last 48 hours there's been 13 influencers like hardmaru and peteskomoroch, discussing topics such as #ICML2020, #RadicalUtuand .
Trends
Top hashtags
Top influencers
hardmaru 
peteskomoroch 
shakir_za 
NandoDF 
ericjang11 
stanfordnlp 
MSFTResearch 
YadKonrad 
hugo_larochelle Top sources
News
Neural Architecture Search
RT @lilianweng: Although popular and successful model architectures are mostly designed by human experts, it doesn't mean we have settled down with the best option. Neural Architecture Search (NAS) automates network architecture engineering in a more systematic way.
https://t.co/qEl9eawRmL
OpenNeural Architecture Search (NAS) automates network architecture engineering. It aims to learn a network topology that can achieve best performance on a certain task. By dissecting the methods for NAS into three components: search space, search algorithm and child model evolution strategy, ...
RT @lilianweng: Although popular and successful model architectures are mostly designed by human experts, it doesn't mean we have settled down with the best option. Neural Architecture Search (NAS) automates network architecture engineering in a more systematic way.
https://t.co/qEl9eawRmL
OpenNeural Architecture Search
Neural Architecture Search (NAS) automates network architecture engineering. It aims to learn a network topology that can achieve best performance on a certain task. By dissecting the ...
That's 17 000 pre-prints.
Happy Friday and Good luck finding the paper you were looking for.
The good news is that now you too can grab a bag of papers from the Public @arxiv_org dataset.
https://t.co/BNliKjfcdt https://t.co/KspBepv1Dm https://t.co/4YZiMMJBCL
OpenLeveraging Machine Learning to Fuel New Discoveries with the arXiv Dataset
To help make the arXiv more accessible, we present a free, open pipeline on Kaggle to the machine-readable arXiv dataset: a repository of 1.7 million articles, with relevant features such ...
RT @apsarathchandar: I am teaching a new graduate-level Machine Learning course @polymtl / @MILAMontreal in Fall 2020 - https://t.co/bkLPVdEqAT. The course is online. If you are a student in any of the Quebec Universities, you can register for the course here: https://t.co/ZY1p8AlelY
OpenINF8953CE - Machine Learning (Fall 2020)
The course, while covering several problems in machine learning like regression, classification, representation learning, dimensionality reduction, will introduce the core theory, which ...
RT @OleWinther1: When learning VAEs, is it possible to get a good signal-to-noise ratio for the importance weighted bound without reparameterization? Yes, and it improves the learning of discrete VAEs! @valentinlievin @andrea_dittadi
Paper https://t.co/bFpNwUeAPg
Github https://t.co/6zsfkSoNyR
OpenClick here to read the article
Score function estimator Without making assumptions about the variational distribution, the gradient of the importance weighted bound (1) with respect to the parameters of the approximate ...
Introducing the NeurIPS 2020 hide-and-seek privacy challenge
Organized by the van der Schaar Lab, the hide-and-seek privacy challenge has been accepted as part of the competition track for NeurIPS 2020
RT @Abebab: "In the spirit of communal values that unifies such a diverse continent, ‘harnessing’ technology to drive development means prioritizing welfare & benefit of local communities, not distant Western start-ups or tech monopolies." https://t.co/bXlNm5LWn0
New paper now live 🥳🥳🥳 https://t.co/gJhpNfTkYh
OpenAlgorithmic Colonization of Africa
By Abeba Birhane. We live in a world where technological corporations hold unprecedented power and influence. Technological solutions to social, political, and economic challenges are ...
RT @shakir_za: I was extremely excited to give a short talk on 'Queering Machine Learning'. Queering is an approach for a more critical ML that is available to us all. Thank you @QueerinAI workshop @icmlconf #ICML2020 🙏🏾🏳️🌈🥳✊🏾. Video, text, slides here 👇🏾
https://t.co/ezXCpGzWs4
OpenQueering Machine
I am incredibly humbled to have been able to give a short talk at the Queer in AI workshop at ICML2020. This is the text of the talk. Watch the video. Look through the slides. What an ...
@jmschreiber91 Do you know a good canonical opendata benchmark dataset / task that we could upload to https://t.co/3awOuqNaqw and use to write an example in the scikit-learn documentation to illustrate this pitfall?
OpenMachine learning, better, together
OpenML: exploring machine learning better, together. An open science platform for machine learning.
RT @ShayneRedford: There are few options for evaluating multilingual question answering outside of English, and especially few for open domain question answering.
Yi Lu, @jodaiber, and I are excited to release an Open QA evaluation set, spanning 26 languages. [1/n]
https://t.co/GK7Lh8OeoY https://t.co/K5eaMqY166
OpenMKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering
Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and A…
Wangaari Maathai's work was a great source of guidance for us @DeepIndaba. We created the Wangari Maathai Impact award to recognise innovation in technogy across Africa for the benefit of society. #RadicalUtu is the philosophy that guides all our efforts. https://t.co/x7UTuaM62v https://t.co/utZCMzpbRx
OpenKambule and Maathai Awards
The Deep Learning Indaba is proud to host the Kambule, Maathai and Umuntu Awards. The Kambule Doctoral Award recognises and encourages excellence in research and writing by doctoral ...
Browse topics
Get updates live! Follow us on
RT @PardoFab: I am thrilled to release Tonic, a new deep RL library 😁🎉
It supports both TensorFlow 2 and PyTorch, is simple and modular, and contains a benchmark on 70 environments from OpenAI Gym, DeepMind Control Suite and PyBullet.
https://t.co/QO6Dwz14Ft https://t.co/wK8uIiXy0Y
OpenTonic
Tonic RL library. Contribute to fabiopardo/tonic development by creating an account on GitHub.
RT @PTKDaily: Bringing an AI Product to Market by: @JustinJDN @peteskomoroch @mikeloukides
Featured in PTK #47 https://t.co/Wu5dx0RpvW
Post: https://t.co/r06uaURQRn
OpenView this email in your browser
The Projects to Know weekly newsletter features 3 academic papers and 3 open source projects that are playing a meaningful role in advancing machine intelligence and data science.
RT @lorenlugosch: NeurIPS rebuttal time. About to make heavy use of @deviparikh et al's rebuttal guide! https://t.co/QJO5c3Ng4B
Open
RT @Trifacta: Where is robotics heading? Read @Forbes article to gain a special view into the minds of leading companies as they share where they’re taking their #AI powered robots. https://t.co/T550RwuPDC
OpenWhere Is Robotics Heading? Perspectives From iRobot (Colin Angle), Stanley Black & Decker, And Robots In Service Of The Environment
With robots increasingly being used in both professional and personal settings, where are we in the current state of robotics and where is the robotics industry heading?
RT @hardmaru: Self-attention mechanism can be viewed as the update rule of a Hopfield network with continuous states.
Deep learning models can take advantage of Hopfield networks as a powerful concept comprising pooling, memory, and attention.
https://t.co/FL8PimjVo9
https://t.co/HT79M95lkn https://t.co/Ld2eioVsDG
Openml-jku / hopfield-layers
Hopfield Networks is All You Need. Contribute to ml-jku/hopfield-layers development by creating an account on GitHub.