PyData Warsaw #9: Deep & Machine Learning + After Party

This will be the 9th PyData Warsaw regular meetup at Centrum Szkoleniowe Adgar Ochota near Warszawa Zachodnia station (English: Warsaw West).

Location: http://en.adgarochota.pl/contact/location

Live Stream: https://www.youtube.com/watch?v=j2yuAyVV0p4

room number: "Event Room"

Doors open at 18:00, talks start at 18:30, about 8pm we move to a pub. We are ready to host 150 folk in the room so there may be plenty of people to discuss data science questions with!

Please remember to unRSVP if you realize you can't make it - it will help a lot for our crew.

And make sure you follow @pydatawarsaw for any updates and early announcements.

Join our Slack:

http://pydata-warsaw.container-labs.com

First Talk:
Grzegorz Kokosiński & Karol Sobczak (Teradata Labs) - "Presto - SQL-on-Anything"
With Presto, an open source distributed analytical SQL engine, it is possible to query different kinds of data sources via an uniform ANSI SQL interface. Presto uses connector architecture that provides an abstraction layer for anything that can be expressed in a row-like format, ranging from MySQL tables, HDFS, Amazon S3 to NoSQL stores, Kafka streams and proprietary data sources. Presto allows anyone to implement a connector and benefit from the capabilities of the Presto SQL engine, enabling them to join data from various sources within a single SQL query. We will additionally show you how to leverage Presto in an analytical, Python based pipeline.

Second Talk:

Marek J. Drużdżel - "A Crash Introduction to Learning Bayesian Networks and Causal Discovery"

Abstract:
Bayesian networks offer an intuitive and theoretically sound tools for modeling uncertain domains. In this talk, I will give a crash introduction to Bayesian networks, to learning them from data, and to an automatic discovery of causal relationships from data.

Third Talk:

Przemysław Strzelczyk (Samsung) - "Deep Learning for Mobile & Embedded Systems – selected topics"

“Low computing power, battery usage and available memory are the main factors that restrict the use of Deep Neural Networks in off-line mode on mobile or embedded devices. In this talk, I will present some methods of learning and optimization of neural networks which can make them suitable for those platforms.”

Fourth Talk:
Sujatha Subramanian - "Recommender systems" - everything you need to know to get started!
We are in the era of hyper personalization where relevant information finds you. Recommender systems are an integral part of making this happen. In this presentation we will discuss about various approaches of Recommender systems. We start with basic models like "Content-based filtering", "Collaborative filtering" and move to advanced implementations that use Stochastic Gradient Descent to do "Matrix factorization" and "Restricted Boltzmann Machine" using Deep Learning with Tensorflow

Agenda:

18:00 - 18:30 - Doors open

18:30 - 18:35 - Introduction

18:35 - 19:05 - First Talk

19:10 - 19:40 - Second Talk

19:40 - 19:50 - Break

19:50 - 20:20 - Third Talk

20:25 - 20:45 - Fourth Talk

20:45 - 20:50 "Speed Dating"

20:50 - 24:00 - After Party - Street Restauracja Blue City

PS1: default language is English, but there may be some exceptions from the rule

PS2: presentation part is mainly Python focused but not only, We expect to host a number of guests working with R, Scala and other languages.

direct contact: pszwed@gmail.com

See you !