en

Zaloguj się

close
Nie masz konta? Zapomniałem hasła

Przypomnij hasło

close Wypełnij formularz.
Na Twój adres e-mail zostanie wysłane link umożliwiający zmianę hasła.
Wyślij
<< przejdź do listy wydarzeń
To wydarzenie już się odbyło. Sprawdź nadchodzące wydarzenia

Data Science Warsaw #43

Wydarzenie:
Data Science Warsaw #43
Typ wydarzenia:
Spotkanie
Tematyka:
IT
Data:
12.02.2019 (wtorek)
Godzina:
18:00
Język:
angielski
Wstęp:
Bezpłatne
Miasto:
Miejsce:
Sala 107 Wydział MINI PW
Adres:
Koszykowa 75
Strona www:
Opis:

The next Data Science Warsaw Meetup will take place on Tuesday, 12th February, and afterward we invite you to the afterparty powered by NETHONE! During the meetup we'll have two talks:


  • Apache Spark on AWS EC2 use case for NLP exercise: Amazon comments mining - Sergiy Tkachuk


In this talk, Sergiy will present how you can leverage power of AWS cloud platform in combination with Apache Spark framework on the example of Amazon comments mining.

As data scientists we are always looking for efficient and cheap ways to prototype and experiment. During the presentation you will learn how to set up the cluster on your own and run Spark tasks using PySpark. You will also see how to set up Jupyter Notebook to communicate with the cluster.


Bio: Sergiy is a Big Data & Advanced Analytics graduate of the Warsaw School of Economics. He works in Schneider Electric as data scientist. He is part of Global Marketing Analytics and AI team and is in charge of global corporate brand analytics. He is passionate about natural language processing and artificial intelligence theory.


  • Understanding neural machinery in text-based processing - Ania Wróblewska, Filip Graliński, Tomasz Stanisławek (Applica.ai)


What is worth to know as a data scientist is not only how to build machine learning models, but also understand their intrinsic mechanisms. We will present a simple but powerful tool to debug the output of supervised models — geval. Geval can give you an insight into what can be improved in the data sets and/or the model.

Moreover, we will present a prototype architecture for automation of processes in text based work and a few use cases for text-based models of various types and explain main findings that are much easier to be discovered using our tool.


  • Anna Wróblewska Senior Data Scientist at Applica / Assistant Professor at Warsaw University of Technology
  • Filip Graliński Senior Deep Learning Engineer at Applica / Teaching Assistant at Adam Mickiewicz University
  • Tomasz Stanisławek Text Mining Consultant at Applica
Widzisz błąd w wydarzeniu? Wydarzenie jest nieaktualne? Poinformuj nas o tym! >>

Pracodawcy IT: Warszawa

Netcompany
Software House

Warszawa
technologie:
,
3 oferty pracy
 
Hicron
Software House

Poznań, Warszawa, Wrocław
technologie:
,
2 oferty pracy
 
Onwelo
Firma technologiczna

Katowice, Kielce, Kraków, Lublin, Poznań, Trójmiasto, Warszawa
technologie:
,
24 ofert pracy
 
Zobacz wszystkie firmy >>

Podobne wydarzenia