Montreal Data

Articles, nouvelles et annonces

How to deploy Machine Learning models as a Microservice using FastAPI
As of today, FastAPI is the most popular web framework for building microservices with python 3.6+ versions. By deploying machine learning models as microservice-based architecture, we make code components re-usable, highly maintained, ease of testing, and of-course the quick response time.

Facebook Enginering: How machine learning powers Facebook’s News Feed ranking algorithm
We use ML to predict which content will matter most to each person to support a more engaging and positive experience. Models for meaningful interactions and quality content are powered by state-of-the-art ML, such as multitask learning on neural networks, embeddings, and offline learning systems. We are sharing new details of how we designed an ML-powered News Feed ranking system.

Kevin De Bruyne uses data analysts to broker £83m Manchester City contract without agent
De Bruyne commissioned data analysts to assess his influence at City and how well they are set up for success in the coming years, based on the age and qualities of the current squad. De Bruyne was able to show City, through data collected, his enduring value to the team as their most influential player, and used this to negotiate a significant pay-rise under the terms of the new deal.

Data Science in Marketing - Case Studies from Airbnb, Lyft, DoorDash
Summarizing articles from official blogs of these companies, we'll get a high level overview of marketing automation and then zoom in on the parts where data science and machine learning play their role.
If you read on, you'll find these three sections: (1) Marketing automation systems, (2) Performance estimation and (3) Optimizing bidding & budget allocation

Predicting FT Trending Topics
Understanding the preferences of Financial Times readers is crucial for improving user experience and maintaining engagement with our products. Trending topics prediction is a data science model built using machine learning and time-series analysis. We define article topics by an unsupervised machine learning algorithm and use time-series analysis to flag anomalies in data.

Événements

Meetup Montréal-Python 85 – Koala Poli
Monday 19 April 2021 @ 18:00
Ce mois si on vous offre:
- Apprentissage machine en robotique par Nicholas Nadeau;
- Module du mois: random par Kouame Kofi;
- Appercu du programme de PyCon 2021 par le coordonateur en chef du commité de programme, Philippe Gagnon.

Meetup PyData Montreal #19
Thursday 22 April 2021 @ 18:00
6:00 pm — Introductions
6:10 pm — "Text Extensions for Pandas" by Frederick Reiss
7:10 pm — "Introducing Elyra: Extending JupyterLab for AI" by Luciano Resende
8:00 pm — Wrap-up

Intelligence artificielle et cybersécurité: protégez vos innovations!
Friday 23 April 2021 @ 12:00
Institut intelligence et données (IID) de l'ULaval: Comment identifier les risques de cybersécurité spécifiques à l’IA? Quelles sont les bonnes questions à se poser en matière de cybersécurité avant de se lancer dans un projet d’IA? Quelles sont les solutions de sécurisation possibles? Comment les choisir et les mettre en œuvre?

Dialogue ouvert : L’intelligence artificielle (IA) au Canada
Tuesday 27 April 2021 @ 13:30
Le Groupe de travail sur la sensibilisation du public du Conseil consultatif en matière d’intelligence artificielle du gouvernement du Canada organise des ateliers virtuels régionaux pour savoir ce que vous et les membres de votre communauté pensez de l’IA.
Ces ateliers permettront de formuler des recommandations au gouvernement du Canada sur la manière de sensibiliser le public à l’IA et de susciter sa confiance dans ce domaine. Les conversations seront axées sur une compréhension de la technologie, ses utilisations potentielles et les risques qui y sont associés.
Chaque atelier dure environ 2,5 h et est gratuit.

Meetup: How to QA your ML models
Wednesday 28 April 2021 @ 16:00
Simon Dagenais from Snitch AI will go through the reasons behind using an efficient validation framework that goes beyond the common metrics used by ML practitioners and why these tests matter when building high-quality models.