the June meetup will be sooner and more exciting than usual:
• Andrew Ng, co-founder of Coursera, director of the Stanford AI Lab, soon Chief Scientist at Baidu
Deep Learning: Machine learning and AI via large-scale neural networks
(via video, starting at 19:30)
Please submit your questions to Andrew here, and vote for interesting ones! This is a joint remote talk with the Paris, Berlin and London machine learning meetups, and every one of the 4 location will be participating in the joint interactive Q&A session following the talk. Many thanks to Igor and Franck from Paris for organizing!
[ link to live streaming ]
We'll also have two local presentations this evening:
• Apache Giraph for Applications in Machine Learning & Recommendation Systems
Maria Stylianou, HPC Software Engineer at Novartis (start 19:00)
Abstract: Over the last years, companies have turned to big data analytics to better understand their customers and drive their services according to customers' needs. In many cases, data is represented in graphs, for instance, describing user connections in a social network or user-item ratings in an online retailer. So far, Hadoop has been the swiss army knife of analytics, but has proven to be inefficient for graph mining and machine learning algorithms. This gave rise to a new generation of processing systems designed for this type of analytics. Apache Giraph is a representative of such systems. In this presentation, we showcase Giraph, its model and characteristics. We then demonstrate its suitability with machine learning algorithms and finally walk through an example algorithm for recommendation systems built on top of Giraph.
[ slides ]
• Smarter than Smart Sharpen - Advances in Image Deconvolution in Digital and Computational Photography
Michael Hirsch, Postdoc at University College London and the Max Planck Institute in Tübingen (start around 20:30)
Abstract: Image Deconvolution is a key area in signal and image processing, that is receiving an ever increasing interest from the academic as well the industrial world due to both its theoretical and practical implications. It involves many challenging problems, including modeling the image formation process, formulating tractable priors incorporating generic image statistics, and devising efficient methods for optimization. This renders image deconvolution an intriguing but also intricate task, which has recently seen much attention as well as progress in both the image and signal processing but also the computer vision and graphics community.
In this talk I will present some recent advances, that not only help sharpen blurry photos but might also change the design of future cameras.
[ slides ]
After the presentations we will move next door to the bQm bar for some socializing and more interesting discussions (right under Polyterrasse, at the ETH main building, around 9pm). They also have screens showing the games.
And even during the meetup, we'll of course keep you updated about the outcome of the Germany-Portugal soccer game!