Let's talk about Artificial Intelligence and Recommender Systems! (PyCon.DE)

Hey Tech Heads,

we joined PyCon.DE as a Meetup Sponsor. So there will be a Data Science Meetup at the evening of the first conference day.

"People buying X also bought Y”, “Discover Weekly”, “Top 10 for You” - personalization of online services by recommendations surrounds everyone in daily life. To personalize content Amazon, Spotify, Netflix and many more use Recommender Systems and Machine Learning. This development comes along with another remarkable trend around learning machines: Deep Learning. Almost daily we hear about the tremendous progress that makes humans obsolete in more and more domains: skin cancer detection, No-Limit-Hold'em Heads-Up Poker, or speech recognition (No, not yet another Alpha-Go example).

Preliminary agenda

18.30: Doors open

19:00–20:00: Deep Learning for Recommender-Systems - Marcel Kurovski (inovex)

During his master thesis at inovex Marcel Kurovski studied the application of Deep Learning for Recommender Systems. He investigated interesting approaches in this emerging research area. In addition, he developed a system for vehicle recommendation in TensorFlow based on data from a large German online market that extends Google’s Wide and Deep Learning approach. In his talk Marcel will share his insights and those of other big players with you. He will also share his impressions from the very recent ACM RecSys Conference 2017 in Como which is the leading conference for recommender systems.

https://secure.meetupstatic.com/photos/event/e/6/0/600_464643680.jpeg

20:00–20:30: Pizza, Beer and Networking

20:30–21:30: Using CNNs for Multi-Instance Multi-Label Image Classification with Sparse Labels - Zoran Cupic (inovex)

Today, Deep Convolutional Neural Networks are one of the most used and most promising techniques for image classification. This becomes apparent looking at results of the ImageNet Challenge, where the best results were achieved with Deep Convolutional Neural Networks.

We will have a look at how Deep Convolutional Neural Networks work in real world problems and under changing conditions.

In his talk Zoran Cupic will present his bachelor's thesis in which he developed and tested an approach for the prediction of several business attributes of a restaurant, only using pictures of it.

Open End