A review of state of the art vision-language models such as CLIP, DALLE, ALIGN and SimVL| AI Summer
Learn everything about one of the most famous convolutional neural network architectures that is widely used on image segmentation.| AI Summer
Understand how positional embeddings emerged and how we use the inside self-attention to model highly structured data such as images| AI Summer
Explaining the mathematics behind generative learning and latent variable models and how Variational Autoencoders (VAE) were formulated (code included)| AI Summer
New to Natural Language Processing? This is the ultimate beginner’s guide to the attention mechanism and sequence learning to get you started| AI Summer
How can we efficiently train very deep neural network architectures? What are the best in-layer normalization options? We gathered all you need about normalization in transformers, recurrent neural nets, convolutional neural networks.| AI Summer
The first article of the GANs in computer vision series - an introduction to generative learning, adversarial learning, gan training algorithm, conditional image generation, mode collapse, mutual information| AI Summer
What are skip connections, why we need them and how they are applied to architectures such as ResNet, DenseNet and UNet.| AI Summer
So far, I’ve written about two types of generative models, GAN and VAE. Neither of them explicitly learns the probability density function of real data, $p(\mathbf{x})$ (where $\mathbf{x} \in \mathcal{D}$) — because it is really hard! Taking the generative model with latent variables as an example, $p(\mathbf{x}) = \int p(\mathbf{x}\vert\mathbf{z})p(\mathbf{z})d\mathbf{z}$ can hardly be calculated as it is intractable to go through all possible values of the latent code $\mathbf{z}$.| Posts on Lil'Log
Machine Learning and Data Science.| Angus Turner
[Updated on 2021-09-19: Highly recommend this blog post on score-based generative modeling by Yang Song (author of several key papers in the references)]. [Updated on 2022-08-27: Added classifier-free guidance, GLIDE, unCLIP and Imagen. [Updated on 2022-08-31: Added latent diffusion model. So far, I’ve written about three types of generative models, GAN, VAE, and Flow-based models. They have shown great success in generating high-quality samples, but each has some limitations of its own.| lilianweng.github.io
We’re on a journey to advance and democratize artificial intelligence through open source and open science.| huggingface.co