Past Meetup

PyData Krakow #2

This Meetup is past

87 people went

Location image of event venue

Details

It will be the second PyData Krakow event. Default language is English.

Venue - The Stage, Łobzowska 3, Kraków (https://www.google.pl/maps?q=the+stage+krak%C3%B3w&um=1&ie=UTF-8&sa=X&ved=0ahUKEwiG9N3yivjXAhXOhrQKHUAdBqgQ_AUICigB)

Speakers:

1. Michal Bigaj - Machine Learning Engineer at Craftinity - How to make a model work for you?

Creating a useful machine learning model is not a simple task. There is a lot of common and uncommon pitfalls. Some of them can be easily avoided, others not. I will show some problems that may occur during creating machine learning solutions and ways of dealing with them.

2. Michal Jamroz - Ph.D. candidate at AGH University of Science and Technology - Image generation using deep learning

Deep learning is particularly successful in computer vision field. Deep models have been achieving state-of-the-art results for a few years in many popular CV tasks like classification, object detection, and segmentation on many benchmark datasets. Besides that, deep learning models are capable of generating artificial samples of data indistinguishable by humans from real ones.
I am going to start my presentation by presenting a topic of image generation in its historical context. I will pay attention to the renaissance of deep learning in the 2000s. Later, I will introduce two most popular classes of models used nowadays - Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). I will discuss how they work and their process of learning. Various extensions and modifications will be also presented. Further, both models will be examined for their applications to semi-supervised learning. At the end, I would like to show some visualizations of data generated by previously discussed models and tell how they can be implemented using popular python libraries like Theano and Lasagne.

3. Bartlomiej Rozkrut - CTO at 2040.io - How to automate user support using machine learning?

- Why automate user support?
- Our experiments with classification, auto-reply and automatic actions in backend
- Supervised learning vs unsupervised learning in real life
- Our results
- Current experiments

----------------------------------------------------------------------------------

Doors open at 18:00, talks start at 18:30 pm. 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.

Make sure you follow @pydatakrakow for any updates and early announcements.

Agenda:

18:00 - 18:30 - Doors open

18:30 - 19:10 - Michal Bigaj - How to make a model work for you?

19:10 - 19:50 - Michal Jamroz - Image generation using deep learning

19:50 - 20:30 - Bartlomiej Rozkrut - How to automate user support using machine learning?

20:30 - After Party

After the event, there will be an After Party at The Stage, venue where the meetup takes place - feel free to grab a beer, share some interesting ideas and play billiards.

----------------------------------------------------------------------------------

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: [masked]