Bit of a Tangent

025 | Self-Supervised Machine Learning: Introduction, Intuitions, and Use-Cases

March 5, 2020

On this episode of Bit of A Tangent, we discuss the emerging field of self-supervised machine learning. This is an immensely exciting area of active research in machine learning and AI - one which most people haven’t even heard about yet! We build up to the intuition for the topic by covering supervised and unsupervised learning; autoencoders and dimensionality reduction, and exploring how these techniques could be applied to Gianluca’s Quantified Self n=1 sleep quality dataset. We culminate in a detailed discussion of the state-of-the-art Contrastive Predictive Coding model, and how it allows us to learn about the structure of the world, without tonnes of labelled training data!




Jared on Twitter:

Gianluca on Twitter:

Bit of a Tangent on Twitter ( and Instagram (

Summer school on Computational Neuroscience:

Control problem in AI:

Coordination problem:

Deep learning overview:

t-SNE explained:

Variational autoencoders explained:

Self-supervised learning by

CPC model papers on Arxiv: 

Blog posts explaining CPC:

Podbean App

Play this podcast on Podbean App