/explore
|
You are here 
|
blog.christianperone.com | ||
| | | | |
thenumb.at
|
|
| | | | | [AI summary] The text discusses the representation of functions as vectors and their applications in various domains such as signal processing, geometry, and physics. It explains how functions can be treated as vectors in a vector space, leading to the concept of eigenfunctions and eigenvalues, which are crucial for understanding and manipulating signals and geometries. The text also covers different types of Laplacians, including the standard Laplacian, higher-dimensional Laplacians, and the Laplace-Beltrami operator, and their applications in fields like image compression, computer graphics, and quantum mechanics. The discussion includes spherical harmonics, which are used in representing functions on spheres, and their applications in game engines and glo... | |
| | | | |
iclr-blogposts.github.io
|
|
| | | | | Diffusion Models, a new generative model family, have taken the world by storm after the seminal paper by Ho et al. [2020]. While diffusion models are often described as a probabilistic Markov Chains, their underlying principle is based on the decade-old theory of Stochastic Differential Equations (SDE), as found out later by Song et al. [2021]. In this article, we will go back and revisit the 'fundamental ingredients' behind the SDE formulation and show how the idea can be 'shaped' to get to the modern form of Score-based Diffusion Models. We'll start from the very definition of the 'score', how it was used in the context of generative modeling, how we achieve the necessary theoretical guarantees and how the critical design choices were made to finally arri... | |
| | | | |
yang-song.net
|
|
| | | | | This blog post focuses on a promising new direction for generative modeling. We can learn score functions (gradients of log probability density functions) on a large number of noise-perturbed data distributions, then generate samples with Langevin-type sampling. The resulting generative models, often called score-based generative models, has several important advantages over existing model families: GAN-level sample quality without adversarial training, flexible model architectures, exact log-likelihood ... | |
| | | | |
kvfrans.com
|
|
| | | In my previous post about generative adversarial networks, I went over a simple method to training a network that could generate realistic-looking images. However, there were a couple of downsides to using a plain GAN. First, the images are generated off some arbitrary noise. If you wanted to generate a | ||
