In the 15th edition of #Kaggle Grandmaster Series, 2x Kaggle Grandmaster Marios Michailidis joins us to share his #datascience journey. https://t.co/DGdVX40UP6 #kagglegrandmaster@StackNet_
Have you ever wondered what it takes to become the top #datascientist in the world? Join us on Aug 18 for a #virtual panel with @srisatish and https://t.co/AHCQLzjMBA’s #Kaggle Grandmasters Guanshuo, @StackNet_, and Olivier Grellier to learn their tips: https://t.co/OCdSzb49Cy
Together with @ph_singer@StackNet_@Kagglenizer and @srisatish we have published an article on the importance of backtesting the covid-19 forecasting models https://t.co/Xz558UUKTP and open sourced the code https://t.co/imOmx1kNHR
Let’s democratize NLP for all languages! 🌎🌎🌎
Today, with v2.9.1, we are releasing 1,008 machine translation models, covering ` of 140 different languages trained by @jorgtiedemann with @marian, ported by @sam_shleifer. Find your language here: https://t.co/9EMtfopij3 [1/4]
The Big Bad NLP Database - More than 400 NLP related datasets spanning multiple languages and different tasks. Also it is being actively updated!
https://t.co/ZfABgo1EyI
@JFPuget@ChrisDeotte@kaggle That is a great achievement @ChrisDeotte ! His kernels and discussion contributions have helped the community immensely.
Also holding the top position for so long was a remarkable feat @JFPuget ! Congrats!
Privileged to be releasing my 2nd interview with THE @kaggle legend, GM: Marios @StackNet_
We continue talking about Kaggle, Marios' work at @h2oai & Their team's 14th Pos sol for Data Science Bowl 2019 comp.
Video: https://t.co/4kkDefFEej
Audio: https://t.co/62YZEZFtoV
People who fail at @kaggle competitions have two reactions:
1 - They start improving their modeling skills
2 - They start Kaggle bashing.
I went to first option.
In these days of @kaggle bashing, here is a great example of value created by a recent Kaggle competition: https://t.co/6qvf0afpWo via @StackNet_#kaggle#MachineLearning
@SE_Norred@WalterReade@randal_olson@ppleskov @MaloyanNarek @kaggle Participants are (almost) never forced to disclose their work to Kaggle or the sponsor. Your argument is wrong.
Exceptions include the Zillow competition (oops). Other exceptions include prize winning. And there you can opt to not accept the prize and not disclose your work.
@_aldoraine You just get the predicted probabilities out and you apply a cutoff if binary (like if pred>0.5 then class 1 else class 0) or you just get the highest probability to get to the right class. Then you draw the confusion matrix manually)#
I would like to thank all our #London#meetup members & guest speakers for being a key part of our growing community. Our group is now one of the biggest #datascience meetups in the world!
Join the @h2oai movement & find a group near you today https://t.co/PYSwX0SA2b
#gratitude
Curious to know more about H2O #DriverlessAI Custom Recipes? Read @StackNet_'s latest #blog to learn how Prophet and pmdarima (for ARIMA) implementations can be integrated with our time series forecasting recipe: https://t.co/56TVH6GL5J #AI#ML