Title: Scalable Time-series Classification
Speaker: Josif Grabocka (University of Hildesheim)
When: 25.05.2019, 16:15
Where: OH 14, E23
Time-series classification is a pillar problem for the machine learning community, particularly considering the wide range of applicable domains. In this talk, the focus is on prediction models that are scalable both in terms of the training efforts, but also with regards to the inference time and memory footprint. Concretely, time-series classification through models that are based on discriminative patterns will be presented. Finally, the talk will end with a recent application on biometric verification.
Title: Generative Models
Speaker: Igor Babuschkin (DeepMind)
When: 13.6.2019 16:15
Where: OH 14, E23
Generative models are a set of unsupervised learning techniques, which attempt to model the distribution of the data points themselves instead of predicting labels from them. In recent years, deep learning approaches to generative models have produced impressive results in areas such as modeling of images (BigGAN), audio (WaveNet), language (Transformer, GPT-2) and others. I'm going to give an overview of the three most popular underlying methods used in deep generative models today: Autoregressive models, generative adversarial networks and variational autoencoders. I will also go over some of the state of the art models and explain how they work.
13.06.2019 Josef Schäfer (ehemals Projektleiter Zensus 2021, Statistisches Landesamt NRW, Düsseldorf)
Titel: "Von der Volkszählung 1987 zum Zensus 2021 - mehr als drei Jahrzehnte amtliche Statistik"
Diplom-Statistiker Josef Schäfer hat mehr 30 Jahre beim Statistischen Landesamt Nordrhein-Westfalen in Düsseldorf gearbeitet. Schwerpunkt seiner Arbeit war anfangs die Volkszählung 1987, später die Entwicklung des Modells eines registergestützten Zensus. Herr Schäfer möchte seine Erfahrungen in der amtlichen Statistik im kommenden Wintersemester auch im Rahmen einer Vorlesung für den Studienschwerpunkt "Amtliche Statistik" einbringen.
Der Vortrag findet am 13.06.2019 um 16.15 Uhr in Raum M/E 21 statt.