Directory
Published directory entries matching your search.
A Towards Data Science article by Hui Wen Goh evaluating popular hallucination detectors, including G-eval, Ragas and the Trustworthy Language Model, across four public RAG datasets. Using AUROC and precision/recall, it reports how well the methods automatically flag incorrect LLM responses in retrieval-augmented generation systems.
lambda-ml is a small machine learning library written in Lisp, specifically Clojure, aimed at simple, concise implementations of machine learning techniques and utilities. It covers supervised algorithms such as neural networks, decision trees, ensemble methods, k-nearest neighbors, linear and logistic regression, naive Bayes and random forest, plus unsupervised methods including DBSCAN, hierarchical clustering, k-means and non-negative matrix factorization.
ManifoldLearning.jl is a Julia package for manifold learning and nonlinear dimensionality reduction. It provides methods including Isomap, diffusion maps, locally linear embedding, Hessian eigenmaps, Laplacian eigenmaps, local tangent space alignment and t-SNE. Most methods use k-nearest neighbors to construct local subspace representation, and a custom k-nearest neighbors function is suggested for large datasets.
MEKA is an open source implementation of methods for multi-label learning and evaluation, based on the WEKA Machine Learning Toolkit. It includes dozens of multi-label methods from the scientific literature and a wrapper to the MULAN framework. The project is distributed via SourceForge, with code hosted on GitHub.
A Scientific American article discussing a new machine learning training method that aims to improve AI generalization abilities similar to human learning. The article suggests that adjusting training approaches, rather than solely increasing training data volume, may lead to more flexible and less error-prone AI systems.
Spinning Up is OpenAI's educational resource on deep reinforcement learning. Its documentation covers installation, included algorithms, running experiments, and an introduction to RL, along with algorithm pages for methods such as DDPG and PPO. The DDPG page describes an algorithm that concurrently learns a Q-function and a policy for continuous action spaces. The PPO page describes on-policy first-order methods, including PPO-Clip.
Accord.NET is a .NET machine learning framework combined with audio and image processing libraries written in C#. It covers classification, regression, clustering, distributions, hypothesis tests and kernel methods, with imaging and signal processing components. The framework is intended for building computer vision, audition, signal processing and statistics applications, including commercial use. It offers sample applications, documentation and a wiki.
Agent Leaderboard is a Hugging Face Space created by galileo-ai that displays interactive leaderboards ranking large language models on agentic tasks. Users can select a task category, evaluation methodology, and performance metric to generate updated comparison tables and visualizations of model performance.
ahaz is an R package providing computationally efficient procedures for regularized estimation with the semiparametric additive hazards regression model. It depends on R version 2.10 or later, along with survival, Matrix and methods, and requires compilation. The package is authored and maintained by Anders Gorst-Rasmussen under GPL-2 and appears in the MachineLearning and Survival views.
Arch Tools provides one API key for 63 tools aimed at AI agents and developers, covering web search, scraping, AI generation, OCR, transcription, crypto data, email and utilities. It supports REST and MCP protocols and offers two authentication methods: an API key or per-call x402 crypto payments in USDC on Base.
Audio diffusion library for PyTorch that includes models for unconditional audio generation, text-conditional audio generation, diffusion autoencoding, upsampling, and vocoding. The models are waveform-based, and the U-Net, DiffusionModel, diffusion method, and samplers are customizable for other formats. No pre-trained models are provided.
This Automatic Speech Recognition Hugging Face Space converts spoken audio to written text. Users can upload audio files, record from their microphone, or provide an audio URL, and select options including language, model, decoding method, and punctuation.
A GitHub collection of graph classification papers with reference implementations, covering embedding, deep learning, graph kernel and factorization methods. It also links to graph classification benchmark datasets and similar curated collections.
Beautiful Soup is a Python library for pulling data out of HTML and XML files. It provides simple methods and Pythonic idioms for navigating, searching, and modifying a parse tree, and it works with parsers such as lxml and html5lib. The project has been used for screen-scraping work since 2004.
CLIPasso is a method for converting an object image into a sketch with adjustable abstraction levels while preserving key visual features. It optimizes Bézier curves using a differentiable rasterizer and a CLIP-based perceptual loss, without requiring an explicit sketch dataset. Abstraction is controlled by varying the number of strokes.
This is the website for the second edition of Data Visualization: A Practical Introduction by Kieran Healy, forthcoming from Princeton University Press. It contains a complete draft of the manuscript, and the book is not yet available for pre-order. According to the preface, the book teaches the ideas and methods of data visualization in a reproducible way.
Datumbox is an open-source machine learning framework written in Java for rapid development of machine learning and statistical applications. It focuses on including many machine learning algorithms and statistical methods and on handling large datasets. The code is licensed under the Apache License, Version 2.0, and releases are available on Maven Central, including version 0.8.2.
A Java scientific and numerical library written by Michael Thomas Flanagan to support his research and undergraduate programming courses. It is distributed as the flanagan.jar package and includes general classes, example programs and arbitrary precision methods. The author has retired and states it will be updated less frequently. Commercial use, public listing of source codes and redistribution are not permitted.
DreamBooth is a method for personalizing text-to-image diffusion models. Given a few images of a subject and its class name, it fine-tunes a pretrained model so a unique identifier refers to that subject, allowing synthesis of the subject in new scenes, poses, views and lighting, with tasks including subject recontextualization and text-guided view synthesis.
ELKI is an open source data mining software written in Java. It focuses on research in algorithms, emphasizing unsupervised methods in cluster analysis and outlier detection, and offers data index structures for performance and scalability. It is designed for researchers and students to extend.
Uncover LLM evaluation's importance and explore methods for assessing its performance and impact across industries.
A blog post summarizing a University of Illinois study on solo performance prompting (SPP), a prompt engineering method in which an LLM summons multiple personas that collaborate on a task. The post describes the SPP prompt structure and reports on three experiments: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle.
GeoLite databases and web services from MaxMind provide free geolocation and limited network data for IP addresses. The data is less accurate than MaxMind's paid GeoIP products. A free GeoLite account is required to download databases or query the web services, which use the same integration methods and documentation as GeoIP with minor modifications.
The mat package from Gonum provides implementations of float64 and complex128 matrix structures and linear algebra operations on them in Go. It offers interfaces for matrix classes, concrete implementations such as Dense and SymDense, methods for using matrix data, and types for matrix factorizations such as QR and LU.
