The previous meetup at Picnic was such a success that we might as well organise another one! On July 25, TomTom will be hosting the 11th Data Science NL Meetup. Join us for an evening of engaging talks, great people, delicious food, two exciting book raffles, and interesting announcements from the community. Many thanks to TomTom for sponsoring and hosting and to O'Reilly for sponsoring the book raffle.
• 5:30 PM: Walk-in with food and drinks
• 6:30 PM: Introduction by Jeroen Janssens
• 6:35 PM: Welcome by TomTom
• 6:40 PM: Talk 1: "Ideas that Constrain Artificial Stupidity" by Vincent Warmerdam
• 7:15 PM: Book Raffle part 1
• 7:20 PM: Talk 2: "Kids just want to have fun. Affect detection in an online learning platform" by Roger Smeets
• 7:55 PM: Book Raffle part 2
• 8:00 PM: Talk 3: "Learning from messy sensor data" by Zeinab Bakhtiarinoodeh
• 8:35 PM: Community Announcements
• 8:45 PM: Drinks
• 9:30 PM: End
• Talk 1: Ideas that Constrain Artificial Stupidity:
Freedom sounds like a good idea but there's a reason why you'd want a fence near a ravine and a speed limit on a car. One might even call it common sense. The problem is that machine learning models don't typically have that and the results can be disastrous. This talk is about celebrating constraints on models in order to improve their applications.
• About Vincent (http://bit.ly/2XK7wWt):
Vincent is an algorithm person who works for GoDataDriven, blogs at koaning.io and has been organising a bunch of conferences/meetups in the last few years. AskHimAnything[tm].
• Talk 2: Kids just want to have fun. Affect detection in an online learning platform:
Squla is an online educational platform for children aged 4-12. Since Squla's mission is to promote fun learning, an important user engagement metric is enjoyment. Timely and automatic detection of (a lack of) enjoyment can be helpful in providing appropriate interventions to keep users engaged. Building models to facilitate the detection of affect (i.e. emotional states) in this context presents two challenges: First, an instrument has to be developed that can be used to identify instances of (lack of) enjoyment while children are playing. Second, this instrument has to be properly understood by children. To this end, we have developed and validated an emoticon-based self-report instrument to derive ground-truth labels of four emotions: Joy, frustration, confusion, and boredom. Training a number of different classifiers for automated affect detection yields promising results, in particular for detecting joy and frustration.
• About Roger (http://bit.ly/2YY1luq):
Roger Smeets (1981) is the head of data science at Squla. He obtained a PhD in Economics from the Radboud University Nijmegen in 2009. He spent the next eight years conducting econometric research in public policy (CPB Netherlands Bureau for Economic Policy Analysis) and academia (Rutgers University, USA). After returning to the Netherlands, he joined Squla in 2017. He currently lives in Amsterdam with his wife and three children.
• Talk 3: Learning from messy sensor data:
In this talk we will discuss how the information created by the multiple sensors, which are integrated in modern smartphones can assist human in a smart way in different domains. We will review Machine Learning techniques and methods to detect events from smartphone sensor data.
• About Zeinab (http://bit.ly/32uHfdB):
Zeinab Bakhtiarinoodeh is a senior data scientist at TomTom, with a strong background in mathematics and computer science. In 2017, she obtained her Ph.D. in Computer Science and Logic from LORIA, Université de Lorraine in France. At TomTom she leverages computer science, machine learning, and mathematical modelling to turn data into a story, and into new fascinating features for the users of TomTom products. She previously worked at EyeOn, where she improved their forecast of new products using machine learning techniques.