scikit-learn API design and NLP and ML for enhanced search

It's time for our first meetup! In this meetup we'll have two talks. One from Lars Buitinck, one of the authors of the popular scikit-learn Python based machine learning library. Another talk is by Arno Veenstra, who is working on natural language processing to enhance the search capabilities on their vast amounts of digital content.

Location and pizza + beer for this meetup is offered by GoDataDriven (http://godatadriven.com/).

Agenda:

• 18.00: Arrive, socialize, have a drink and eat pizza

• 18.50: Short introduction by your humble organizers

• 19.00: Talk 1, by Arno Veenstra, Data Scientist at Sanoma

Enhanced search using NLP and machine learning at Sanoma

Sanoma operates 200+ websites and 100+ print magazines, generating large amounts of original content. In the effort to make this content universally accessible by the entire organization, there is a content library for which the search capabilities are enhanced using natural language processing and other machine learning techniques. This talk is about the models and implementation of this system.

• 19.45: short break

• 20.00: Talk 2, by Lars Buitinck, eScience Engineer at Netherlands eScience Center

API design for machine learning software: experiences from the scikit-learn project

scikit-learn is an increasingly popular machine learning library. Written in Python, it is designed to be simple and efficient, accessible to non-experts, and reusable in various contexts. This talk concerns design choices for the application programming interface (API) of the library, with a focus on composability and reusability.

• 20.45: more drinks and social talks

• 21.30 or later: everybody out! (out of the room, that is; there is a bar in the next room)