List of talks at PyCon SK 2018

All Machine Learning / AI Community / Diversity / Social Data Science DevOps Documentation Education Python General Security Soft Skills Hardware Web Development Other

Differentiable programming in Python and Gluon for (not only medical) image analysis
English flag Talk Machine Learning / AI

Jan Margeta (SK)

This talk explores how writing machine learning models can become simpler and more fun with dynamic code execution. The "deep learning" paradigm is rapidly becoming "differentiable programming".
And we will see it applied to cardiac medical images and images from industrial inspection.
It is based on our experiences at KardioMe in making of machine learning apps for healthcare and optical inspection in manufacturing. We will have a peek into python pipelines for data preparation for creation of anatomical models for virtual reality and 3d printing.

Traditional development and deployment of deep learning models often feels like stepping away from programming and what we love about Python. Simple loops and branches get replaced with special operations. Programs are written as static computation graphs which need to are compiled to optimize runtime and resource usage. Seeing intermediate results and debugging can be a pain, even with specialized tool. Tensorflow, Keras, Theano, MxNet, CNTK, they all do that.

Machine learning is all teaching computers how to solve the problems for us with data instead of explicitely telling them how to do so. It is undoubtedly a different way of thinking about programming.
Yet, it does not need to become unnecessarily complex and you certainly do not need a PhD for that.

Gluon, is a new dynamic interface to MxNet and is a fenomenal tool to develop models that improve with data. The network can be written like a regular program with ifs or loops. Everything is dynamically executed and even allows step by step debugging with pdb. The program parameters are, however, trainable so that the execution output gets better with more data.

These together are massive helpers in faster experimentation and more fun. In addition to that, Gluon has a large zoo of pretrained models ready for your next app and MxNet as its backend is fast and resource efficient, and can be deployed to embedded devices too.

Industrial Machine Learning: Building scalable distributed machine learning pipelines with Python
English flag Talk Machine Learning / AI

Alejandro Saucedo (GB)

This talk would provide useful and practical understanding on how to build industry-ready machine learning models in python through distributed, horizontally-scalable architectures. I will include why and when these architectures are required, best practices, caveats, technologies to use them, and a practical implementation using celery + rabbitmq.

Introduction to Machine Learning with Python
English flag Workshop Machine Learning / AI

Katharine Jarmul (DE)

In this half-day workshop, we'll take a walk through a Kaggle competition on house prices to explore our dataset. Then, we'll build a model to submit our predictions to Kaggle. Finally, we'll introspect what our model has learned. By the end of the course, you should have an idea of how to get competing on Kaggle or building your own models with Python and scikit-learn.

Students are expected to arrive ready to learn and with all packages properly installed. There will also be some theoretical discussions on machine learning practices, and some group work.

GitHub Repo: https://github.com/kjam/intro-to-ml

Real-time personalized recommendations using embeddings
English flag Talk Machine Learning / AI

Jakub Mačina (SK)

Recommender systems are successfully used in several domains, e.g. product or movie recommendation. In e-commerce, the aim is to provide personalized suggestions to users for relevant items out of all products available.

In this talk, I will focus on item recommendation for anonymous users when no historical data about user is available (also referred as a cold-start problem) and challenges we have encountered. Firstly, I will dig deeper into similar item recommendation by NLP model comparing textual descriptions of items. This approach is based on word embeddings extracted from neural network models, such as word2vec or fasttext.

Finally, I will talk about how to apply the same idea of word embeddings to learn a representation of each product. With the product embedding representation, it is easy to calculate similarities between products in real-time. Moreover, we found out that product embeddings are able to capture style of a product, color, category or a price level.

All of the examples will be practical using data about restaurants reviews and fashion products. Open-source NLP library Gensim is used in code samples. Presentation will be supported by visualization of embeddings to get the idea behind. Everybody with any interest in machine learning is welcome. After the presentation, you will know how to compute relationship between pizza and pasta or how to capture a fashion style of a user.

Real-time transcription and sentiment analysis of audio streams; on the phone and in the browser
English flag Workshop Machine Learning / AI

Aaron Bassett (GB)

Discover how you can use Artifical Intelligence to perform sentiment analysis of an audio stream, in real-time! In this workshop, we’ll show you how to use AI and NLP to figure out what a person is calling about and how they are feeling, all from a telephone call audio feed via WebSockets.

In this workshop, we’re going to learn how to create a virtual rapporteur. A digital assistant who can join any conference call; record it and provide participants with real-time insights into the overall tone of the call. Once the call is complete, we’ll look at how we can use the call recording to provide participants with a text transcript as well as meta information about the call such as the most talked about concepts, keywords and entities.