Top 15 Papers From #Google_AI Research Accepted By #NeurIPS2020
https://analyticsindiamag.com/top-15-papers-accepted-from-google-ai-research-by-neurips-2020/
@ml_nlp_cv
https://analyticsindiamag.com/top-15-papers-accepted-from-google-ai-research-by-neurips-2020/
@ml_nlp_cv
Analytics India Magazine
Top 15 Papers From Google AI Research Accepted By NeurIPS 2020
This year, the NeurIPS committee has accepted more than 40 research papers submitted by Google researchers.
یکی از ارائه های جالب کنفرانس #NeurIPS2020 که به صورت آنلاین در حال برگزاری است.
Charles Isbell | You Can't Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise · SlidesLive
https://slideslive.com/38935825/you-cant-escape-hyperparameters-and-latent-variables-machine-learning-as-a-software-engineering-enterprise
Charles Isbell | You Can't Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise · SlidesLive
https://slideslive.com/38935825/you-cant-escape-hyperparameters-and-latent-variables-machine-learning-as-a-software-engineering-enterprise
SlidesLive
Charles Isbell · You Can't Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise
Insights about the future of #Machine_Learning model training from top panelist at NeurIPS, live on youtube today 12th_December #ML #NeurIPS2020 #Backpropagation
https://beyondbackprop.github.io/
@ml_nlp_cv
https://beyondbackprop.github.io/
@ml_nlp_cv
Machine Learning on Knowledge Graphs @ #NeurIPS2020
A timely digest of NeurIPS 2020 by Michael Galkin. He speaks on improvement over Query2Box, how NAS and meta-learning works in KG domain, constructing the queries from the natural language, and several KG datasets. Worth a read!
#Graph_ML
@ml_nlp_cv
A timely digest of NeurIPS 2020 by Michael Galkin. He speaks on improvement over Query2Box, how NAS and meta-learning works in KG domain, constructing the queries from the natural language, and several KG datasets. Worth a read!
#Graph_ML
@ml_nlp_cv
Medium
Machine Learning on Knowledge Graphs @ NeurIPS 2020
Your guide to the KG-related research in NLP, December edition
#NeurIPS2020 tutorial
There and Back Again: A Tale of Slopes and Expectations
Videos are available here:
https://t.co/NUt7wcRYTm
Slides are here:
https://t.co/o8tCFd3iga
@ml_nlp_cv
There and Back Again: A Tale of Slopes and Expectations
Videos are available here:
https://t.co/NUt7wcRYTm
Slides are here:
https://t.co/o8tCFd3iga
@ml_nlp_cv
YouTube
There and Back Again: A Tale of Slopes and Expectations (NeurIPS-2020 Tutorial) - YouTube
👌
Google AI Blog: Google @ #NeurIPS2020
http://ai.googleblog.com/2020/12/google-at-neurips-2020.html
@ml_nlp_cv
Google AI Blog: Google @ #NeurIPS2020
http://ai.googleblog.com/2020/12/google-at-neurips-2020.html
@ml_nlp_cv
Top #NeurIPS2020 picks by GoodAI team | GoodAI
https://www.goodai.com/top-neurips-2020-picks-by-goodai-team/
@ml_nlp_cv
https://www.goodai.com/top-neurips-2020-picks-by-goodai-team/
@ml_nlp_cv
baby-vision: Self-supervised learning through the eyes of a child
آموزش یک شبکه self-supervised از طریق چشم یک کودک در طول دو سال رشد او. در این پژوهش طریقه شکل گیری بازنمایی های بصری سطح بالا نشان داده می شود.
Paper: https://arxiv.org/abs/2007.16189
Github: https://github.com/eminorhan/baby-vision
#NeurIPS2020
@ml_nlp_cv
آموزش یک شبکه self-supervised از طریق چشم یک کودک در طول دو سال رشد او. در این پژوهش طریقه شکل گیری بازنمایی های بصری سطح بالا نشان داده می شود.
Paper: https://arxiv.org/abs/2007.16189
Github: https://github.com/eminorhan/baby-vision
#NeurIPS2020
@ml_nlp_cv
Paper Explained: Principal Neighbourhood Aggregation for Graph Nets
A nice explanation by Andrei Margeloiu about #NeurIPS2020 paper on how to "fix" GNN's expressivity for continuous node features.
@ml_nlp_cv
A nice explanation by Andrei Margeloiu about #NeurIPS2020 paper on how to "fix" GNN's expressivity for continuous node features.
@ml_nlp_cv
YouTube
Principal Neighbourhood Aggregation for Graph Nets (Paper Explained)
*Overview*: Graph Neural Networks (GNNs) can't fully exploit the expressivity of graph-structured data because the current aggregation methods don't meaningfully extract the statistics of the neighbourhood messages. They propose a new general-purpose aggregator…