Past Events

Generative Adversarial Networks - when neural networks fight each other

Deep Fake? Self-Driving Cars? Generative Adversarial Networks are neural network, which are used in wide-range of Problems. This month Jules Salzinger, will give us a intuitive introduction on how these Generative Adversarial Networks work.

AI in Banking & Finance

DI Gernot Griesbacher shared his techniques in statistical modeling and machine learning methods used in the field of banking and finance.

Genetic Programming and Symbolic Regression

Dr. Gabriel Kronberger, Professor for Business Intelligence and Data Engineering at University of Applied Sciences Upper Austria will give us an overview of his research. More about him and his team can be found at: https://heal.heuristiclab.com/content/josef-ressel-centre-symbolic-regression

NLP Essentials: The Bread and Butter - Andi Rexha

PhD Researcher Andi Rexha will present to us the essentials needed in natural language processing. Whether its making chatbots, sentiment analysis or predicting stocks, Andi will give you the foundation blocks needed for such tasks. If you want to learn more about traditional NLP methods and Word embeddings this meetup is for you.

Generating Fake Images - Adrian Spataru

Adrian Spataru will give an overview of approaches used in generative modeling in images. Topics such as variational autoencoder, generative adversarial networks, and deep autoregressive models will be covered. This talk is catered to an audience, who wants to learn the intuition of these models. However, we will talk also about the state of the art approaches (Deep AR), so there is something interesting for more experienced practitioners.

The Secret Sauce of Robotics - Mykhailo Rimel

Mykhailo Rimel from Grenoble INP will present us how AI is used in Robotics.

Time Series Data Forcasting - Maximilian Toller

This month PhD Researcher Maximiliam Toller will give us a practical overview of time series forecasting techniques. With the progress of IoT, Industry 4.0 and online metrics, time series data has become a staple in organizations. After this talk, we hope that the viewers will have a better understanding of the methods and approaches dealing with time series.

Inglorious LSTMs Generating Tarantino Movies with Neural Networks - Bohdan Andrusyak

Bohdan Andrusyak will show us, how to generate a movie script based on old Tarantino movies. Bohdan will show us step by step on how to create our own neural network to generate such scripts. With the knowledge gained in the presentation, you will be able to apply the knowledge to make your own text generator.

Gradient Boosting Workshop - Anand Subramoney & Adrian Spataru

Gradient Boosting is a machine learning algorithm used mostly for regression and classification task. Such Methods have been used successfully to win machine learning competitions on Kaggle. Furthermore, gradient boosting is being more and more used in the industry. In this workshop, we will go first through the theory to get a better intuition and understanding. Finally, we will analyze different case studies and provide practical tips on using gradient boosting in your projects.
The Workshop is split into 2 parts:
1. Part - Anand Subramoney will give a theoretical overview of Gradient Boosting.
2. Part - Adrian Spataru will present how you can apply different implementations of the algorithm and present several case studies.

Dealing with Imbalanced Data - Adrian Spataru

Imbalanced data is a common problem in lots of domains, such as Fraud detection, Disease detection etc. In this talk, we will cover different methods for dealing with such problems. For example: SMOTE, ADASYN, Feature Learning and more.

Transfer Learning Overview & Finetuning Tutorial - Adrian Spataru

Transfer learning is a machine learning method where a model trained for a domain is reused as the starting point for a model on a related domain. In this presentation, we explore different transfer learning techniques and explore the different type of pretrained models (Image, NLP) at our disposal. Furthermore, there will be a tutorial on finetuning for image recognition tasks.

Hawkes Processes Tutorial - Tiago Santos

Hawkes processes are a stochastic method for modeling discrete, inter-dependent events over continuous time. Problems like these can be found in a lot of domains. In finance, an event can represent a transaction on the stock market that influences future prices. In geophysics, an event can be an earthquake that is indicative of other earthquakes in the vicinity.

Reinforcement Learning & Google DeepMind Talk - Anand Subramoney

Reinforcement Learning Tutorial - Talk about the two main classes of learning algorithms (value-based learning and policy-based learning) with examples

Google DeepMind Talk - Talk about following deep mind papers: • Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015). • Mnih, V. et al. Asynchronous Methods for Deep Reinforcement Learning. arXiv:1602.01783 [cs] (2016).

Dockerize Your Data Science Environment - Florian Geigl

A Presentation on the open source Docker container used at Detego for all data science related tasks, followed by a live demo and some best practices.

Predicting Instagram Likes - Adrian Spataru

Can we predict likes in online social networks? What makes a post "attractive"? In this presentation, we will try to answer these questions.

Machine Learning 101 with Scikit-Learn - Adrian Spataru

Understand the basics of Machine Learning and build your first model.