Once we go from training one model to training hundreds of different models with different hyperparameters, we need to start organizing. We’re going to break down our organization into three pieces: experiment tracking, hyperparameter search, and configuration setup.
Link
Diffusion models are a new class of state-of-the-art generative models that generate diverse high-resolution images. They have already attracted a lot of attention after OpenAI, Nvidia and Google managed to train large-scale models. Example architectures that are based on diffusion models are GLIDE, DALLE-2, Imagen, and the full open-source stable diffusion.
Link
Skopeo works with API V2 container image registries such as docker.io and quay.io registries, private registries, local directories and local OCI-layout directories.
Link
Many web projects have moved to the single-page application model. To use this model with Django, you build a project where Django is the back end accessed through a REST API. The Django Ninja library is a FastAPI-inspired tool kit for turning Django views into REST API endpoints with very little extra code. Along the way, you’ll be using curl, a command-line tool that allows you to grab the contents of a web page.
Transfer learning refers to the process of pre-training a flexible model on a large dataset and using it later on other data with little to no training. It is one of the most outstanding 🚀 achievements in Machine Learning 🧠 and has many practical applications.
Link
Kubernetes became a de-facto standard in recent years and many of us - both DevOps engineers and developers alike - use it on daily basis. Many of the task that we perform are however, same, boring and easy to automate. Oftentimes it’s simple enough to whip up a quick shell script with a bunch of kubectl commands, but for more complicated automation tasks bash just isn’t good enough, and you need the power of proper language, such as Python.
Multi-armed bandits have now been studied for nearly a century. While research in the beginning was quite meandering, there is now a large community publishing hundreds of articles every year. Bandit algorithms are also finding their way into practical applications in industry, especially in on-line platforms where data is readily available and automation is the only way to scale.
Link
How do you get live notifications from a service that doesn’t support live notifications? Can you watch an online store for price drops? Or track comments on someone else’s YouTube video? Or at work, can you react to changes in another
Link
New users can start creating straight away. Lessons learned from deployment and improvements to our safety systems make wider availability possible. Link
Recently, graph neural network (GNN) has become the new state-of-the-art approach in many recommendation problems, with its strong ability to handle structured data and to explore high-order information. However, as the recommendation tasks are diverse and various in the real world, it is quite challenging to design proper GNN methods for specific problems. In this tutorial, we focus on the critical challenges of GNN-based recommendation and the potential solutions.
Link
This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations, and the website renders these as side-by-side formatted notes. We believe these would help you understand these algorithms better.
Link
