The Data Science Initiative (DSI) is an initiative that aims to create an environment where anyone with a passion for Data Science can learn this field at an introductory, intermediate, and/or advanced level. The initiative’s main objective is to equip students with the right skills to enter the growing and expanding market of data science.
17:00 – 17:20 – Automated Machine Learning – An Overview by Fatos Ismali
In recent years we have seen an upsurge of Machine Learning techniques being applied to almost all kinds of problems types: classification, regression, clustering, market basket analysis, and many more. This has become a challenge for the typical Data Scientist who is usually faced with a search space of algorithms and configurations that is usually too time-consuming and practically inefficient to go through. In this talk, we introduce the topic of Automated Machine Learning and more specifically automated feature engineering, model selection, hyper-parameter tuning, and neural architecture search.
17:20 – 17:25 – Q&A
17:25 – 17:55 – Overview of Generative Modelling, GANs & adversarial attacks by Jakub Langr
Until recently, generative modeling of any kind has had limited success. But now that Generative Adversarial Networks (GANs) have recently reached few tremendous milestones (and truly exponential growth in the interest in this technology), we are now closer to a general purpose framework for generating new data.
Now GANs can achieve a variety of applications such as synthesizing full-HD synthetic faces, to semi-supervised learning as well as defending and mastering adversarial examples, we can discuss them in this talk. In this talk, we will start with the basics of generative models, but eventually, explore the state of the art in generating full HD images as presented in https://arxiv.org/abs/1710.10196 and dive into adversarial attacks and why this matters to all computer vision algorithms.
17:55 – 18:00 – Q&A