What we're about

This meetup series are for anybody who is interested in technical aspects of Data Science and Machine Learning.

According to our format each meetup we host two talks:

• one by Yandex where Dev team present their cutting edge technology and a use case in one of Yandex services

• another one by guest expert from local industry or academia on a same covered topic

The main goal of these events and whole Y-DATA initiative is to build stronger academia-industry relationships and to make our ecosystem more competitive.

Y-DATA school is a new program in Data Science in Tel Aviv and Ben-Gurion University campus organized by Yandex and operating as a branch of Yandex School of Data Analysis (YSDA). YSDA was founded in Moscow in 2007 and has more than 850 graduates. For many years YSDA is considered the best M.Sc level program in ML and DS in Russia and its graduates work in leading companies and research institutes all over the world.

Visit our website (http://bit.ly/ydata-website)

All Meetup Videos are published on our Youtube (http://bit.ly/youtube-ydata)channel:

Follow our Fb page (http://bit.ly/fb_ydata)

To learn more about Y-DATA:

https://yandex.com/company/blog/ydata-2020

Upcoming events (1)

CatBoost: Inside Look and Industry usecases

Taboola.com Ltd.

Y-DATA Meetup #11 CatBoost: Inside Look and Industry Usecases Hosted by Taboola Talks are in English More info about Y-DATA (Yandex School of Data Science at TAU and BGU) is here: http://bit.ly/ydata-website Previous meetup videos are here: http://bit.ly/youtube-ydata ------- Intro: Gradient boosting is a powerful machine-learning technique that achieves state-of-the-art results in a variety of practical tasks. For a number of years, it has remained the primary method for learning problems with heterogeneous features, noisy data, and complex dependencies: web search, recommendation systems, weather forecasting, and many others. CatBoost is a popular open-source gradient boosting library with a whole set of advantages: 1. CatBoost is able to incorporate categorical features and text features in your data with no additional preprocessing. 2. CatBoost has the fastest GPU and multi GPU training implementations of all the openly available gradient boosting libraries. 3. CatBoost predictions are 20-60 times faster then in other open-source gradient boosting libraries, which makes it possible to use CatBoost for latency-critical tasks. 4. CatBoost has a variety of tools to analyze your model. ----------- Agenda: 18:00 - 18:30 Registration, Mingling, Snacks & Beer 18:30 - 19:15 Talk 1: “Gradient Boosting for data with both numerical and text features” Anna Veronica Dorogush, head of Machine Learning Systems group at Yandex 19:15 - 19:30 Break 19:30 - 20:00 “CatBoost A-Z: from experiments to production” Aviv Nahon, Data Scientist at Riskified 20:00 - 20:30 - "CatBoost in Deep Reinforcement Learning General Conversation Dialog Systems" Slava Alipov, head of NLP and Dialog Systems Group at Yandex ----------- Talk Details and bio can be found here: http://bit.ly/38zeqPE

Past events (10)

ML in Cybersecurity: two sides of a coin

Checkmarx

Photos (81)