GUT-AI Foundation — AI/acc

AI/acc — inaugural post -------------------------- AI for accelerationism and accelerationism for AI. AI/acc Manifesto coming soon! CC: @kourouklides, @kleitos14, @Neurosyncretic_, @goldErebus, @jakobdylanc, monkerrr

WOW MY DMS ARE POPPING WITH WOMEN AND THEY ARE MAAAAD I didn't realize I'd be the one to break this Tea nonsense to the masses. Oopsies. Im single, ladies btw.

The Laplacian pyramid is the ancestor of the wavelet transform. Defines a compact multiscale representation by iterative lowpass/highpass filterings. en.wikipedia.org/wiki/Pyramid_(…

Optimization algorithms come with many flavors depending on the structure of the problem. Smooth vs non-smooth, convex vs non-convex, stochastic vs deterministic, etc. en.wikipedia.org/wiki/Mathemati…

Oldies but goldies: A. Brandt, Multi-Level Adaptive Solutions to Boundary-Value Problems, 1977. Introduces the multigrid method, which is the fundamental tool to speed up the convergence of low frequencies for the resolution of PDEs. en.wikipedia.org/wiki/Multigrid…

Take a function f on ℝ³ and integrate it over all planes. These integrals define the Radon transform of f. Can we recover the function f from its Radon transform? A beautiful inversion theorem says Yes! It's amazing this stuff has applications in #Tomography. #math #calculus

Kronecker products allow you to visualize the entirety of many recursive algorithms in simple tensor diagrams. Let's try to do this for the famous Fast Fourier Transform. But first, consider its easier cousin, the Hadamard: This is analyzed using the "master theorem" of…

This is prolly the most interesting thing I've read on Wiki - The Gaussian complexity and Rademacher complexity are related by an equality. en.wikipedia.org/wiki/Rademache…

RADEMACHER COMPLEXITY: Widely used in Empirical Process Theory and Machine Learning (Philippe Rigollet) ocw.mit.edu/courses/18-657…

Lean Formalization of Generalization Error Bound by Rademacher Complexity arxiv.org/abs/2503.19605 We formalize the generalization error bound using Rademacher complexity in the Lean 4 theorem prover. Generalization error quantifies the gap between a learning machine's…

Lean formalization of generalization error bound by Rademacher complexity. ~ Sho Sonoda, Kazumi Kasaura, Yuma Mizuno, Kei Tsukamoto, Naoto Onda. arxiv.org/abs/2503.19605 #ITP #LeanProver

Clarke derivative generalizes the notion of convex subdifferential to nonconvex locally Lipschitz functions — thanks to Rademacher’s theorem — as the convex hull of the limiting sequences of gradient converging. ams.org/journals/tran/…

Hadamard–Rademacher–Walsh transform is the Fourier transform on the group (Z/2Z)^n, and enjoys a N*log(N) fast transform. It is used among other thing in error correcting codes. en.wikipedia.org/wiki/Hadamard_… en.wikipedia.org/wiki/Walsh_fun…

Oldies but goldies: J.L. Walsh, A closed set of normal orthogonal functions, 1923. Defines the Hadamard–Rademacher–Walsh ortho-basis, which is the Fourier transform on the group (Z/2Z)^n. Used to define error correcting codes. en.wikipedia.org/wiki/Hadamard_… en.wikipedia.org/wiki/Walsh_fun…

Only + and - operations: Walsh-Rademacher-Hadamard vs Haar transforms. Dense vs sparse (for piecewise constant inputs). en.wikipedia.org/wiki/Hadamard_… en.wikipedia.org/wiki/Haar_wave…

The world’s first mosquito air defense system

It is simple! #lab

The controversial women-only Tea app has reportedly suffered a data breach Users from 4Chan posted personal info they found through an exposed database

Brave browser blocks Windows feature that takes screenshots of everything you do on your PC

Google Researchooors promoting their BS and junk science online. 😂🤣🤣 Zero degree of dignity. All they want is to pump the price of their stocks.