Data Fest Minsk
Data Fest is an informal conference that unites researchers, engineers and other data science folks:
- No bullshit! Each speaker is a mature practitioner.
- Broad coverage of topics from non-overlapping domains.
- Not just conference, but also a great party networking.
Data Fest will be held in a secret place in Minsk.
10:00 Make ML Great Again! – Alex Natekin, Dictator at ODS.ai and Founder at DM Labs
10:45 – Free mic session
The aim of this brief session is to expand your data science connections. It is an excellent opportunity for everybody to present themselves to the audience and say a couple of words on their projects and interests related to data science. The presentation format is a two-minute talk and a one-minute question-answer part.
11:45 How to build a self-driving car (in 100 lines of code) – Fedor Chervinskii, Research Engineer at Yandex
Overview of the technology stack inside a modern autonomous vehicle with focus on perception. Different approaches and problem formulations; deep learning for self-driving cars. Mediated perception: semantic segmentation, object detection, depth estimation. Training data: real and simulated
12:30 Objects segmentation on satellite images (Kaggle DSTL Contest, 2nd place) – Artur Kuzin, CV Analyst at Avito
An overview of objects segmentation approaches on satellite images from Kaggle competition (Dstl Satellite Imagery Feature Detection). The speech will be dedicated to hacks and tricks of training and design deep convolutional neural networks collected from top-5 teams.
14:30 From Jupyter notebook to production environment – Petr Ermakov, Data Science and Big Data Team Lead at Mail.ru
In his speech he will overview the long way from the proof of concept models to highload production maintenance.
15:15 How machine learning helps to find effective prices for goods – Alexey Chernobrovov, Director at Jet4Retail
Review of approaches to pricing. How it was before and how machine learning will change it. The theory and practice. A few examples of the implementation of this approach at a large online stores.
16:15 ARIMA vs long term forecasts – Anton Lebedevich, independent contractor
Every textbook that has a time series chapter mentions ARIMA so it became a goto model for forecasting. But in real world it struggles with missing data, public holidays, non-stationarity, several steps ahead predictions. Anton will show better alternatives to ARIMA for long term forecasting.
17:00 Explain me like I'm 5 – Mike Korobov, Software Engineer at ScrapingHub
ELI5 is a Python library which allows to visualize and debug various Machine Learning models. It has built-in support for several ML frameworks and provides a way to explain black-box models. Mike is ELI5 core developer who will tell us more how this magic works.
18:15 Sentiment analysis: best practices and challenges – Vitalii Radchenko, Data Scientist @ Ciklum
Sentiment analysis is a very interesting task where there are many techniques which work well. We will cover data preprocessing, traditional ML, word- and char-based neural networks. Moreover, you will find out different tricks how to deal with small datasets, dataset absence and transfer learning.
Participation is absolutely free! However, you have to register to pass in, hurry up!