💡In our preprint, we first explore two emerging paradigms for image compression, & then introduce:
1) an ultra-low rate textual transform for perceptual compression & denoising,
2) an LZ "transform” with applications to classification, denoising & generation
(continued)
in math, we don't say "everyone has a soulmate"
instead we say "for every ε > 0, there exists a δ > 0 such that
|f(x)-f(x0)| < ε whenever |x-x0| < δ"
and i think that's beautiful
Words can't describe the energy in the room at the Ann S. Bowers Women's Brain Health Initiative launch, so I'll leave the heavy lifting to this short film.
Humor can subvert, enrage, empower & educate. So take a look and then let's get to work.
https://t.co/DI5G6ozUAB
"Neural Manifolds" have become increasingly widespread in neuroscience (&AI), but we are far from having a unified framework. Here are some resources I've found particularly insightful about what neural manifolds are and the role they play in computation in neural systems: 🧵1/14
Functions are vectors! This perspective lets us apply the tools of linear algebra to computational problems from image and geometry processing to machine learning and light transport—and provides a natural explanation for Fourier series.
Let's explore: https://t.co/gxweWoZbjf