Turn live audio into stunning visuals.
Directory
Search the directory
Search published websites, apps and repositories.
AIToolbox is a toolbox of AI modules written in Swift, covering graphs and trees, support vector machines, neural networks, PCA, K-Means and genetic algorithms. The framework uses the Accelerate library to speed up computations, except the Linux package versions. A Swift Package is available for Mac and Linux, described as a sub-set of the full framework.
AIWatch is a real-time status monitoring site for 47 AI services, including Claude, ChatGPT, Gemini, Cursor and Codex. It lets users check whether AI services are down and track uptime and incidents, showing service status at a glance and flagging outages for immediate confirmation.
albumentations is a fast, flexible open-source image augmentation library. An academic paper describing the library is available. The project is no longer maintained, and AlbumentationsX is presented as its successor.
Alibi is an open-source project that provides algorithms for explaining machine learning models. Developed by SeldonIO and hosted on GitHub, it includes installation and usage documentation for pip and conda.
Alibi Detect is an open-source project that provides algorithms for outlier, adversarial, and drift detection. Developed by SeldonIO and hosted on GitHub, it includes installation and usage documentation for pip and conda.
Alien Dreams: An Emerging Art Scene - ML@B Blog provides machine-learning models, research, training resources, or evaluation tools.
Alpaca is a project that provides code and documentation to train Stanford's Alpaca instruction-following LLaMA models and generate associated training data. It includes details on the data release, data generation process, and fine-tuning procedures.
alpaca-lora is a repository with code for reproducing the Stanford Alpaca results using low-rank adaptation (LoRA). It provides an Instruct model and training code that can be easily extended to the 13b, 30b and 65b models, along with a script for downloading and inference.
Altern is a directory for finding AI tools, curated lists and categories, with a searchable index of AIs, a weekly leaderboard, tasks and alternatives. Its help center covers user accounts, saving tools, and suggesting alternatives.
Ambrosia is a cross-platform command line tool written in Go for improving text datasets used in machine learning. It offers fast deduplication, filtering, length checking and whitespace trimming, plus an LLM-based filtering option called psort. It ships as a single binary with no dependencies and is pre-1.0 software.
A Java Toolbox for Scalable Probabilistic Machine Learning.
A work-in-progress inpainting branch of Stable Diffusion, published as a public Replicate model. The model runs on Nvidia A100 (80GB) GPU hardware and predictions typically complete within 11 seconds. It costs approximately $0.015 to run on Replicate, or 66 runs per $1. It is open source and can be run on a computer with Docker.
Understand how large language models work under the hood.
Apache cTAKES is an open-source project developed under the Apache Software Foundation. Its documentation and project resources are hosted on a GitHub repository, and it is part of the broader Apache developer and user community.
Apache MXNet is a deep learning framework mixing symbolic and imperative programming. It includes a dynamic dependency scheduler that parallelizes symbolic and imperative operations, with a graph optimization layer for symbolic execution. The repository was archived on Nov 17, 2023, and is read-only.
XAI — Company → News · API docs · · GitHub.
XAI — Company → News · · API console · GitHub.
APIDNA provides machine-learning models, research, training resources, or evaluation tools.
Applied ML is a curated collection of papers, articles and blogs about data science and machine learning in production, organized under topics such as data quality, recommendation, search and ranking, and MLOps. It is licensed under MIT and covers how organizations frame problems and which techniques worked.
Architecture Helper is an AI-powered architecture design analysis tool. It can analyze building photos for styles, history and design details, and re-render a photo of a home or room in a chosen style. It also offers city architecture guides. The first analysis and the first restyle are free, with no account needed.
As limitações da sensação tecnológica de 2023: o ChatGPT IAgora?
astroML is a Python module for machine learning and data mining built on numpy, scipy, scikit-learn, matplotlib and astropy, distributed under the 3-clause BSD license. It provides statistical and machine learning routines for analyzing astronomical data, loaders for open astronomical datasets, and examples of analyzing and visualizing datasets. The project was started in 2012 to accompany a textbook on statistics, data mining and machine learning in astronomy.
An overview of the current attack techniques on LLMs by Marcello Carboni.