J’ai regardé quelques séries de conférences vraiment très bien. Ca remplace bien des séries Netflix.
Cours à la fois de science et de philosophie ;) On peut voir que les deux sont intrinsèquement liés.
Jean Marc Jancovici, l’énergie Cours des Mines (plutôt orienté ingénieurs donc) sur les différentes énergies. Quantitatif: voici les enjeux, voici les chiffres, voici ce à quoi on peut s’attendre. Sujet et personnage très clivant, mais fascinant.
Neural Networks: From Zero to Hero
Incroyable de clarté.
It starts with making your own autograd engine in 100 lines of python, similar to PyTorch and then builds up to a GPT network. Andrej Karpathy is one of the best in the field, founder of OpenAI, then Director of AI at Tesla. Nothing like the scam tutorials that just copy-paste random code from the internet.
Il semble que Deep Learning for Coders de fast.ai soit très bien aussi.
Un thread récent sur HN m’a donné quelques idées.
Statistical rethinking How to interpret scientific data.
This course teaches data analysis, but it focuses on scientific models first. The unfortunate truth about data is that nothing much can be done with it, until we say what caused it. We will prioritize conceptual, causal models and precise questions about those models. We will use Bayesian data analysis to connect scientific models to evidence. And we will learn powerful computational tools for coping with high-dimension, imperfect data of the kind that biologists and social scientists face.
Human Behavioral Biology, Robert Sapolsky
A thorough look on some of our behaviors through the lens of hormones, neural/nervous system, and how evolution shaped us. Also, Pr Sapolsky is a great speaker with a complete deadpan humor.
Only people who have thought about concepts deeply over a lifetime can deliver such truly delightful lectures. If you have an hour to spare, just listen to the first lecture [2] and it will profoundly impact your outlook on science (and physics in particular)
The Maths of General Relativity
We build together the theory of general relativity, with a visual and intuitive approach.