Deep Learning Meetup Summer 17

Dear Deep Learning enthusiasts,

I'm really looking forward to seeing you all on Monday.

First talk will be by Philip Kessler, understand.ai, Karlsruhe:

Vita: Philip Kessler studied computer science at the KIT where he built an autonomous driving model car and specialized in machine learning. He worked for Mercedes Research in the Silicon Valley before he founded understand.ai, a machine learning startup specialized in creating training data for machine learning algorithms.

Abstract:Missing training data is one of the biggest bottlenecks in AI at the moment and not only solvable by poor interns labeling your data in-house. This talk will be about what possibilities you have to get annotated data and how we create them ourselves in an efficient way.

Second talk will be Léo Paillier, deepomatic, Paris:

Abstract: Building a dataset from scratch can quickly become a grueling task involving hundreds of man-hours spent carefully tagging images or even annotating single pixels to perform segmentation. Although there's no magic solution Domain Adaptation provides an easy way to harness the knowledge from a similar but different dataset. We will have a look at the different trending approaches and how they relate to each other. We will encounter Adversarial training, Denoising Auto-encoders and Generative Adversarial networks.

Vita: Leo Paillier is a Research Engineer specialized in Deep Learning for Computer Vision at Deepomatic, a company dedicated to providing computer vision based software solutions and services to businesses. He previously combined his passions for AI and programming in a Master of Science in Computer Science and then later another one in Mathematics and Machine Learning.

Third Talk will be by Edward Zimmermann, Redcley Partners, Munich:

Abstract: We'll explore using deep learning to improve urban traffic signaling. Bicycles (both self-powered and pedelecs) are the future of urban transport alongside (self-driving) electric cars, buses, and rail services. Green waves make cycling more efficient, attractive, and safer. Instead of fixed ""green wave"" timings or priorities, a work in progress system is presented that learns to increase the flow of bicycle traffic while minimizing the impact on other traffic actors -- and in many use cases also results in improvements in general traffic times. Using low power efficient SoCs -- Tegra X1 -- the ""smarts"" are integrated in traffic lights and provide V2I interfaces -- also to mobile phones of cyclists -- about signal changes and warn of pedestrians or cyclists. Dispensing with inductive loop, magnetometer, or radar-based sensors buried in the pavement makes the system inexpensive. We'll present initial results from pilot testing in a German city.

Vita: Edward Zimmmermann has worn many hats throughout his career, including that of a mathematician, national economist, market/social researcher, computer scientist, and entrepreneur. A dominant focus of his R&D over the past 20+ years has been text retrieval, metadata, data mining, knowledge discovery, pattern recognition, natural language processing, and machine learning. Edward has been a part of many publically funded projects, working with German, EU, and UN organizations, and has collaborated with a number of research institutes and national scientific agencies. Parallel to the rapid development of GPGPUs, he renewed his interest in computer vision, artificial neural networks, and reinforced learning. Edward recently became involved as a consultant in a number of applications of deep learning. His involvement with traffic sprang from discussions with Michael Hartig, managing director of GESIG Germany, which is a partner on the project.

See you on monday.

Best

PS: Unfortunately, we cannot let you in if you are not properly registered. Also, please free your space if you cannot come.