This is a Telegram bot that lets you chat with the chatGPT language model using your local browser. The bot uses Playwright to run chatGPT in Chromium, and can parse code and text, as well as send messages. It also includes a /draw command that allows you to generate pictures using stable diffusion. More features are coming soon.
Link
Game-playing artificial intelligence (AI) systems have advanced to a new frontier. Stratego, the classic board game that’s more complex than chess and Go, and craftier than poker, has now been mastered. Published in Science, we present DeepNash, an AI agent that learned the game from scratch to a human expert level by playing against itself.
Link
Diagrams lets you draw the cloud system architecture in Python code.
It was born for prototyping a new system architecture without any design tools. You can also describe or visualize the existing system architecture as well.
Diagram as Code allows you to track the architecture diagram changes in any version control system.
Link
A well-established rule of thumb that applies to most machine learning projects is that the larger and cleaner the dataset, the better the performance.
Link
GeoTorch is a python library on top of PyTorch and Apache Sedona for deep learning and scalable data processing focusing on raster imagery and spatio-temporal non-imagery datasets. It has various modules for deep learning and data preprocessing under both categories of datasets. The deep learning module offers ready-to-use datasets, models, and
[Link]{https://kanchanchy.github.io/geotorch/}
This post is related to the recent release of a new open-source project called OpenMetricLearning (OML), and one of its goals is to lower the entry threshold for metric learning pipelines. We will briefly introduce the theory, discuss the examples in code and show how simple heuristics can perform on a level comparable with the current SotA. Since the project is new, each star on GitHub is essential for us.
Time series forecasting is an essential scientific and business problem and as such has also seen a lot of innovation recently with the use of deep learning based models in addition to the classical methods. An important difference between classical methods like ARIMA and novel deep learning methods is the following.
Link
Ray AI Runtime (AIR) is an open-source toolkit for building ML applications. It provides libraries for distributed data processing, model training, tuning, reinforcement learning, model serving, and more.
Link
Text-to-image has advanced at a breathless pace in 2021 - 2022, starting with DALL·E, then DALL·E 2, Imagen, and now Stable Diffusion. I dug into a couple of papers to learn more about the space and organized my understanding into a few key concepts
Link
This Not That is a suite of tools for working with, exploring, and interacting with “data maps”. A data map is a two (or three) dimensional representation of higher dimensional vector space data, usually produced by UMAP, t_SNE, or another manifold learning technique.
Link
