Machine Learning and Digital Regulation
summary
Covers how companies run production machine-learning pipelines using large-scale data collection and streaming (referred to as “big quarry” and “data flow”), with concrete impacts like Netflix attribution and a deployed driving‑support tool that predicts recurring weekday danger patterns. Describes algorithms used (k‑NN, SVM, random forests, neural nets/deep learning), emphasizes data preprocessing and an A/B testing validation workflow, and raises concerns about algorithmic digital regulation (régulation numérique).
AI-written summary · about
chapters (18)
- 0:00Introduction
- 2:25ML applications
- 5:33Data as ML cornerstone
- 7:57Regression and classification
- 11:05Correlation vs causality
- 13:10Cost functions and learning
- 16:38Model selection
- 18:46Clustering algorithms
- 22:11Data visualization
- 25:25Avoid known patterns
- 27:11Segmenting space
- 29:18Data preprocessing
- 31:26Main algorithms
- 35:58Neural networks
- 38:47Variable selection
- 40:29Model validation
- 42:54ML as a service
- 43:56Digital regulation
related talks
06mMachine learning is about your data and deployment
27mA Look Inside Applied Machine Learning
33mMachine Learning in the age of increasing Data Privacy Consciousness
49mThe Impact of Machine Learning in Companies
21mHow The Application Of Machine Learning Is Changing The Way Companies Use Data
22mReal-world applications of machine learning: Beyond the hype
16mDeep Learning in Production Seen by a Data Engineer
24mMachine Intelligence gets real