Sublime
An inspiration engine for ideas
My excellent student @LinYorker has put together a 6-part blog that introduces natural gradient and Riemannian gradient methods in detail:
https://t.co/oGZwTj1juy
A version of his method won the 2021 NeurIPS Approximate Inference in Bayesian Deep Learning Competition.
Mark Schmidtx.comUnderstanding convolutional neural networks from first principles. A great opportunity to learn about circulant matrices, shift-equivariant layers, discrete Fourier transform, CNNs, receptive field... and play with @JuliaLanguage
All the details here👇
https://t.co/P5ifI6nhTJ https://t.co/90ZS09oYas
Marc Lelarge 🌻x.com
Natural gradient with momentum on submanifolds:
In Riemannian normal coordinate systems, metric tensor becomes identity but computationally intractable.
We introduce generalized normal coordinates https://t.co/D82DD38hQz
Black–Litterman is a portfolio allocation model developed by hardcore quants at Goldman Sachs.
Not a hardcore quant at Goldman Sachs?
Not a problem.
Here's a step-by-step guide using Python: https://t.co/IJQAOlE3Q2
New notebook! To get to grips with discrete flow matching paper, I've put together a little notebook to test it on MNIST. I kept the article's notations so it's easy to follow alongside the article!
🐍 notebookv1: https://t.co/HsHTMjC7wF https://t.co/w43qP2nLKp
Georges Le Bellierx.com
Deep Learning and Computational Physics - Lecture Notes, University of South California
Great and concise notes on various fundamental topics in deep learning, drawing connections between computational physics and deep learning. The notes got a nice structure. Starts from the very basics, gradually to some DL... See more
@giffmana Great read! You may find this blog from @ppwwyyxx interesting. It goes into details of different resize/resample options in CV libraries and their consequences. This understanding helped us a lot back in the days: https://t.co/w8UVA7S6yz
Alexander Kirillovx.com🚀 Looking forward to a foundtional humanoid motion tracker?
📢Meet Any2Track — Track Any Motions under Any Disturbances!
💡Any2Track shows SOTA performance on diverse motions under multiple disturbances.
Project: https://t.co/9obGq0e2qN
Codebase:... See more
Zhikai Zhangx.com