Data Science Louvain-la-Neuve, edition #5!

Our Data Science Meetup LLN series continues:

When: 19th March at 7 PM
Where: Auditorium Sainte-Barbe Ba94, place Sainte-Barbe 1, 1348 Louvain-la-Neuve.

Agenda:

19h15 - "Machine Learning: Getting Back Into the Loop: Machine learning provides powerful predictive tools, yet it leaves users with little opportunity to control decision making. First, models are often hard to understand and decisions are consequently difficult to interpret. Second, the mechanics of algorithms cannot be easily altered to integrate user feedback (e.g. because he/she is not happy with some predictions). Third, the statistical nature of machine learning algorithms makes it difficult to enforce domain constraints. In this talk, I will show three examples of methods to address those limitations. First, I will discuss recent works on interpretability for dimensionality reduction, in particular with MDS and t-SNE. Then, I will show how priors can be used to embed user feedback in Bayesian PCA. Finally, I will present ongoing work on constraint enforcement for decision trees."
by Prof. Benoit Frénay (University of Namur)

20h15 - "Contaminant analysis: For a company in manufacturing, we have built a machine learning model to detect the type of contaminant detected on medical grade plastic using Xray images, photos, Infrared pictures as a source. The application is fully deployed in the cloud and is going into production now. (model integrated in an application that will be used by all lab technicians around the world). " by Simon Dubrulle (Data scientist at Keyrus)

The talks will be followed by an opportunity to enjoy a beer and a chat.

We hope to see you all there!

The organizers:

Mihailo Backovic- B12 Consulting
Gaël de Lannoy- GSK
Thibault Helleputte- DNAlytics
Michel Herquet- B12 Consulting
John Lee- UCLouvain
Paul Smyth- GSK
Michel Verleysen - UCLouvain