The Deep Learning Workshop is a pre-conference event of the 5th Swiss Conference on Data Science – SDS|2018.
Date: Wednesday, June 6, 2018
Venue: GS1 Schweiz, Monbijoustrasse 68, Bern
Deep Learning methods have shown significant success in tackling some of the major long-standing challenges in Machine Learning. Particular applications to Image Analysis, Speech Recognition, Natural Language Processing and many others demonstrate the important advances in this field.
In this workshop, we review some of the major trends, with a focus on applications that are becoming viable for the industry.
Zurich University of Applied Sciences
Deep learning has matured considerably in the last years. We still see astounding applications and more and more pattern recognition use cases solved, which furthers the current hype about AI. But we also see a growing body of theory that explains results, best practices that accelerate prototyping, and a general understanding of the methodology that facilitates real-world use cases.
This talk explores current research results in deep learning and their impact on daily (non-research) work.
Speaker : Thilo Stadelmann | Zurich University of Applied Sciences
Thilo Stadelmann is senior lecturer of computer science at ZHAW School of Engineering in Winterthur. He received his doctor of science degree from Marburg University in 2010, where he worked on multimedia analysis and voice recognition. Thilo joined the automotive industry for 3 years prior to switching back to academia. His current research focuses on applications of machine learning, especially deep learning, to diverse kinds of data. He is head of the ZHAW Datalab and vice president of SGAICO, the Swiss Group for Artificial Intelligence and Cognitive Sciences.
Algorithmic transparency and interpretability. The why, what and who
Deep Learning. Everybody wants it, only a few have it and nobody understands it. Machine learning based black boxes, e.g., convolutional neural networks demonstrated to be very powerful. But they lack interpretability and transparency. In this talk I will discuss why its time to get serious about algorithmic transparency and to bring the discussion to the public domain.
Speaker: Marcel Blattener | Tamedia
Marcel is a data surfer and loves to explore the universe of bits and bytes. He is crazy about all sorts of neural networks and loves to think about backpropagation and renormalization groups while climbing a mountain with his bike. Currently he works at Tamedia as Chief Data Scientist and successfully accomplished diverse Machine Learning projects. Marcel holds a Phd in theoretical physics.
Modern artificial intelligence with deep learning did gain a lot of traction last years. Of course this asks for justification and validation. In this talk I will explain what had to happen that deep learning was so successful and will highlight general use case that work already today. The intention is to give the audience the understanding of the current development on the market and to see behind the hype in the press.
Speaker: Marc Stampfli | Nvidia
Marc Stampfli is responsible to develop the market for NVIDIA in Switzerland. He has a master in computer science from University of Zurich and has more than 17 years of experience in developing new market segments for enterprise companies. Before NVIDIA, he was working for major technology companies from Silicon Valley such as IBM, Oracle, but as well traditional companies such as Colt Technology Services and PricewaterhouseCoopers in leading roles. He is an enthusiastic speaker that is explaining difficult technological topics in simple words so that everybody can follow and understand.
Poster Session / Coffee