8th Machine Learning NL Meetup (Official) hosted by ING

Save the date! The Machine Learning NL sequence continues at ING in Amsterdam on September 20th. This meetup has the same formula as the previous ones. Food (Indonesian buffet), 3 in-depth talks (real business cases and insights from corporates and start-ups about applied Machine Learning), networking + drinks.

> All attendants need to register individually (no guests allowed).
> There will be a video shooting for an after movie. Attendants might be filmed. Please wear a purple hat with yellow stipples if you don't want to appear in the after movie. Thx!

Program
6PM Walk-in with Indonesian buffet

6:30 Intro by Lars Crama - Strategy & Innovation Advisor.(https://www.linkedin.com/in/larscrama/)

6:40 Talk 1: Bas Geerdink, Tech Lead at ING & Tasos Kachrimanis, Sr. Data Scientist at ING - 'Data science at ING: automatic classification of income and expenses'.
https://www.linkedin.com/in/geerdink/
https://www.linkedin.com/in/akachrimanis/
https://www.ing.com

7:25 Talk 2: Jorrit Glastra, CTO/ Deep Learning Lead at Quantib - 'Deep learning for medical imaging: building on from conventional analysis'.
https://www.linkedin.com/in/jorritglastra/
https://www.quantib.com

8:00 Talk 3: Davide Zambrano, Deep Learning R&D at Sightcorp - 'Deep Learning applied to Face Analysis'.
https://www.linkedin.com/in/davide-zambrano-89689b115/ http://sightcorp.com

8:35 Drinks
9:30 End

Visit https://aigents.co for a curated overview of events and career opportunities for AI & Machine Learning Engineers.

Abstracts

Abstract talk 1
Data science is at the core of ING’s business. We are a data-driven enterprise, with ‘analytics skills’ as a top strategic priority. In this session, ING’s data scientists will give a high-level overview of machine learning at ING and go in-depth into two key models that are used in production: the detection of income and expenses.
In several business processes the detection of a customer’s payment behavior is essential. For example, to approve a loan the bank wants to know how much a prospect earns and how her credit rating is. Traditionally, this behavior is classified by a human. But increasing demands from regulators and rising customer expectations on user friendliness and speed required a fresh look on this topic. ING choses to automate (parts of) this work by creating machine learning models. We will give an overview of two of these key models; income and expense detection. We’ll also look ‘under the hood’ and share some results from running the models in production.

Abstract talk 2

Abstract talk 3
Face analysis has recently become the topic of interest for both press and science due to the implications that this technology has for our own life and privacy. Indeed, our face is inherently related to our identity, and this information can be used for identification purposes, such as unlocking our phone. Our face is also being used to extract personal information, such as age, gender and emotion, for commercial or statistical purposes. Therefore, given the delicate aspects of this technology, the problem has to be treated carefully. From a Machine Learning point of view, face analysis can be defined as, given an image, the extraction of necessary features to detect a face and then to identify personal information from it. Face detection needs to be the first step of any face analysis system, while auxiliary tasks such as age, gender, pose, smile classification, or even identification can follow from the extracted detection. How do we properly detect a face? How do we learn these face-related features? In this talk, I will show how Deep Learning has revolutionized computer vision for face detection and I will review the common architectures that can be used to tackle this problem. In particular, I will speak about the Single-Shot Multibox Detector (SSD) architecture as well as the implications of varying image resolutions on the detection of faces.