Awesome GitHub RepositoriesDimensionality Projection Plots

Visdom is a tool for scientific experiment tracking and real-time data monitoring. It provides a programmatic interface for broadcasting live plots, rich media, and training metrics from scripts to an interactive web dashboard. The project specializes in high-dimensional data analysis, offering capabilities to project complex feature sets into 2D space using t-SNE and visualize PyTorch model embeddings. It organizes visualizations into named environments, allowing users to isolate different experimental runs and compare plots across these environments in a single view. The system covers a br

This project is a collection of PyTorch learning resources and educational guides designed to teach the construction and training of neural networks. It serves as a comprehensive deep learning tutorial covering various model architectures and practical implementation strategies. The resources provide specific guidance on implementing computer vision tasks, such as image classification and synthetic imagery generation, as well as reinforcement learning agents using value networks and experience replay. It also covers sequential data modeling through recurrent networks and generative modeling u

This project is a manifold learning and non-linear dimensionality reduction library used to project high-dimensional data into lower-dimensional spaces while preserving topological structure. It functions as a parametric embedding framework and a topological data visualization library for identifying clusters and patterns within complex datasets. The library distinguishes itself through parametric neural mapping, which uses neural networks to learn functional mappings that allow for out-of-sample projections and the reconstruction of original data. It supports supervised and semi-supervised d

NonEuclidean is a graphics framework and rendering engine designed to compute and display three-dimensional scenes using non-standard spatial rules and geometries. It serves as a visualization tool for exploring complex mathematical spaces where traditional Euclidean laws of distance and angle do not apply. The project implements custom rendering pipelines to visualize non-standard geometric projections and warped spatial logic. This includes the ability to map non-Euclidean coordinates to Poincaré disk or Klein models to render curved space on flat screens. The system utilizes dynamic metri

Ce projet est une bibliothèque de machine learning fournissant une collection d'implémentations pour des algorithmes d'apprentissage supervisé et non supervisé. Il sert de framework de deep learning, de collection de classificateurs statistiques et de suite d'outils pour l'apprentissage non supervisé et la réduction de dimensionnalité. La bibliothèque permet la construction de réseaux de neurones, incluant des perceptrons multicouches et des réseaux convolutifs pour la reconnaissance de formes. Elle fournit également des outils pour effectuer l'analyse en composantes principales et l'apprentissage de variétés (manifold learning) pour visualiser des jeux de données de haute dimension, ainsi qu'une suite d'algorithmes de clustering qui regroupent des données non étiquetées par partitionnement itératif. Le projet couvre un large éventail de capacités de modélisation prédictive, incluant des tâches de classification et de régression utilisant des arbres de décision, les k-plus proches voisins, les classificateurs de Bayes, les machines à vecteurs de support (SVM) et la régression ridge. Il inclut également des outils pour les flux de travail de classification d'images et l'analyse de données non étiquetées.

Orange3 is a visual data mining platform that provides an interactive canvas for building data analysis workflows without writing code. At its core, it offers a widget-based visual programming environment where users connect configurable components to perform data preprocessing, machine learning model training, statistical evaluation, and interactive visualization. The platform is built on NumPy-backed data tables with domain descriptors that define variable names, types, and roles, and includes a lazy SQL query proxy for working with database tables without loading all data into memory. The

This is an interactive notebook-based course that teaches machine learning from Python fundamentals through deep learning and natural language processing. It uses real datasets and multiple frameworks within a structured, hands-on curriculum that combines concise explanations with executable code cells, built-in datasets, and embedded exercise checkpoints. Learning progresses through data preparation and exploration, classical machine learning workflows, computer vision with convolutional neural networks, and natural language processing with deep learning, all delivered as a cohesive progressi

Linfa est un framework de machine learning classique et une suite d'apprentissage statistique implémentée en Rust. Il fournit une collection d'algorithmes pour l'apprentissage supervisé et non supervisé, axés sur les méthodes statistiques traditionnelles telles que la régression, le clustering et les arbres de décision. La boîte à outils se distingue par sa capacité à être compilée en WebAssembly, permettant aux modèles analytiques de s'exécuter dans des environnements de navigateur. Elle emploie une interface d'algorithme basée sur des traits pour standardiser le processus d'entraînement et de prédiction à travers ses divers modèles. La bibliothèque couvre un large éventail de capacités, notamment la classification supervisée et la régression de valeurs continues. Elle fournit le clustering non supervisé, des méthodes d'ensemble pour l'agrégation de modèles et le traitement du signal via l'analyse en composantes indépendantes. La suite inclut également des outils de prétraitement de données étendus pour la normalisation des caractéristiques, la vectorisation de texte et la réduction de dimensionnalité utilisant PCA et t-SNE. Des utilitaires supplémentaires sont fournis pour la gestion des données, y compris l'importation CSV et la génération de jeux de données synthétiques, ainsi que des outils d'évaluation de modèles tels que les matrices de confusion et les métriques de validation croisée.

Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and performance. It serves as an interpretability dashboard for large language models and a general performance analyzer for text, image, and tabular datasets. The project distinguishes itself through a comprehensive suite of interpretability tools, including salience map generation for feature attribution, the creation of synthetic and counterfactual examples to test robustness, and the projection of high-dimensional embeddings into visual spaces via UMAP or PCA. It further enable

Scanpy is a Python library for the preprocessing, visualization, and analysis of large-scale single-cell gene expression datasets. It serves as a toolkit for single-cell RNA sequencing analysis, providing a framework to process and analyze genomic data from individual cells to identify biological markers and cell types. The library includes a scalable data processing pipeline for cleaning and preparing genomic data, a clustering framework for grouping cells with similar expression profiles, and a system for modeling transitions between cell states to reconstruct biological development and dif

TensorFlow Similarity is a Python framework designed for training neural networks to learn high-dimensional vector representations and perform similarity-based retrieval. It provides a comprehensive toolkit for metric learning, enabling the development of systems that group similar items together in vector space and identify them through distance-based comparisons. The library distinguishes itself by integrating specialized training techniques, such as contrastive and triplet-based learning, with robust data management tools that ensure stable model convergence. It supports self-supervised re