Awesome GitHub RepositoriesRegularization Techniques

Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and

This project is an open-source, interactive educational platform designed to teach deep learning through a comprehensive, code-first curriculum. It provides a structured learning path that covers foundational mathematics, modern neural network architectures, and practical optimization techniques, enabling practitioners to master complex artificial intelligence concepts through hands-on experimentation. The platform distinguishes itself by integrating technical explanations with executable Jupyter notebooks. This design allows readers to modify code and hyperparameters in real-time, facilitati

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Fastai is a high-level deep learning library built on PyTorch that provides a unified interface for managing the entire machine learning lifecycle. It functions as a comprehensive training toolkit, abstracting hardware management and automating complex training loops to simplify the construction and execution of neural network models. The framework is distinguished by its notebook-centric development environment and a type-dispatching data pipeline that automatically applies transformations based on input data formats. It emphasizes transfer learning through discriminative layer-wise optimiza

This project provides a collection of machine learning algorithms implemented from scratch in Python. It serves as an educational resource using interactive notebooks that combine code with mathematical explanations to demonstrate the first principles of data science. The repository includes reference implementations for neural networks, such as multilayer perceptrons with backpropagation, and supervised learning models including linear and logistic regression. It also covers unsupervised learning through k-means clustering and Gaussian anomaly detection. The codebase covers a broad range of

This repository is an educational collection of deep learning implementations designed to demonstrate the fundamental principles of neural network architecture and optimization. It provides a comprehensive resource for understanding machine learning through hands-on code examples, ranging from basic multilayer perceptrons to complex generative models. The project distinguishes itself by emphasizing the manual construction of models, including the implementation of backpropagation from scratch to illustrate core mathematical mechanics. It covers a wide array of architectural design patterns, s

DINOv2 is a self-supervised vision transformer foundation model designed to generate high-quality visual representations from raw image data. By leveraging large-scale unlabelled datasets, the framework learns to extract robust numerical embeddings that serve as inputs for various machine learning and analysis workflows. The model distinguishes itself through a teacher-student training framework that utilizes centered and sharpened soft probability distributions to align feature maps across multiple image crops. It incorporates a masking strategy that forces the model to reconstruct missing i

This repository collects illustrated single-page cheat sheets that compress the core topics of Stanford's CS 230 deep learning course into visual reference summaries. The collection covers convolutional neural networks, recurrent neural networks, and practical training techniques, pairing schematic diagrams with mathematical notation to bridge intuition and formal understanding. The cheat sheets are organized by subject area and link related concepts across topics, such as connecting vanishing gradients to LSTM gates, to reinforce the full deep learning workflow. Practical training advice on

PyTorch Metric Learning is an open-source library for training neural networks to produce similarity-preserving embedding spaces. It provides a modular framework where interchangeable loss functions, mining strategies, and evaluation tools can be composed to learn representations that map similar items to nearby points and dissimilar items to distant points in the embedding space. The library distinguishes itself through a highly configurable architecture that separates concerns across several interchangeable components. Users can assemble custom loss functions from pluggable distance metrics

GluonTS es un framework para el pronóstico probabilístico de series temporales, diseñado para predecir valores futuros como distribuciones de probabilidad con intervalos de confianza. Soporta tanto el entrenamiento de modelos tradicionales como el pronóstico zero-shot, donde modelos preentrenados generan predicciones para nuevas series sin entrenamiento adicional. El proyecto se distingue por integrar una amplia variedad de enfoques de pronóstico en un flujo de trabajo unificado. Esto incluye arquitecturas de aprendizaje profundo como redes neuronales recurrentes y convoluciones causales, así como la integración de modelos estadísticos externos, la librería Prophet y paquetes de R. El kit de herramientas proporciona una superficie integral para la ingeniería de datos de series temporales, cubriendo el escalado de conjuntos de datos, la división y la transformación de datos temporales sin procesar en tensores. También incluye un conjunto de herramientas de evaluación para medir la precisión del pronóstico y los intervalos de incertidumbre, así como utilidades para la persistencia de conjuntos de datos utilizando formatos como Arrow y Parquet. El framework soporta el despliegue de modelos de pronóstico dentro de la infraestructura en la nube.

GluonTS es una librería de series temporales probabilísticas y framework de pronóstico de aprendizaje profundo. Proporciona un kit de herramientas para construir, entrenar y evaluar arquitecturas de redes neuronales que predicen valores futuros como distribuciones de probabilidad para cuantificar la incertidumbre. El proyecto se distingue por soportar el pronóstico zero-shot e integrar diversos enfoques de modelado, incluyendo redes neuronales probabilísticas profundas y envoltorios para librerías estadísticas externas como Prophet y R forecast. Implementa primitivas arquitectónicas especializadas como convoluciones causales y redes residuales invertibles para prevenir la fuga de información y mapear representaciones latentes en distribuciones de probabilidad válidas. El framework cubre una superficie de ingeniería de datos integral, incluyendo escalado de series temporales, transformaciones biyectivas y modelado jerárquico. Utiliza Apache Arrow y Parquet para el streaming de conjuntos de datos de alto rendimiento y la gestión de acceso aleatorio. Para la evaluación de modelos, incluye una suite de evaluación para medir la precisión del pronóstico y la cobertura probabilística utilizando métricas como la pérdida de cuantiles y puntuaciones de probabilidad de rango continuo. La librería soporta el despliegue de modelos a través de la integración con Amazon SageMaker.

This project is a collection of comprehensive guides and reference materials designed for technical interviews, machine learning system design, and professional development. It serves as a technical knowledge base and a career coaching manual, providing structured resources to help candidates navigate the machine learning hiring landscape. The resource distinguishes itself by offering detailed frameworks for comparing industry roles, analyzing company types, and planning long-term career progression. It provides specific guidance on evaluating employer organizational health, identifying resea

Este proyecto es una librería integral para transfer learning y adaptación de dominio en visión artificial. Sirve como un framework para alinear distribuciones de características entre datasets de origen y destino, un kit de herramientas para la generalización de dominio y una librería para el aprendizaje semisupervisado utilizando pequeños datasets etiquetados y grandes conjuntos no etiquetados. La librería proporciona capacidades especializadas para la adaptación de dominio no supervisada, incluyendo el uso de redes adversarias, arquitecturas basadas en discrepancia y traducción de imagen a imagen para reducir el desajuste de distribución. También incluye herramientas para la generalización de dominio para garantizar la fiabilidad del modelo en dominios de destino no vistos a través de mezcla de estilos y minimización de riesgo invariante. El proyecto cubre una amplia superficie de capacidades, incluyendo la adaptación de tareas y el ajuste fino con regularización especializada, entrenamiento semisupervisado mediante pseudo-etiquetado y aprendizaje de consistencia, y selección de modelos de transfer learning utilizando métricas de transferibilidad. También incluye un gestor de datasets para automatizar la adquisición y preparación de benchmarks de visión estandarizados. La librería incluye utilidades para el monitoreo y la observabilidad, como visualizaciones t-SNE y métricas A-distance para analizar distribuciones de características y discrepancia de dominio.

This project is a computer vision pipeline and volumetric rendering system used to transform photos and videos into high-fidelity 3D models. It implements a deformable neural radiance field framework that optimizes deformation fields to represent non-rigid moving subjects in three dimensions. The system utilizes volumetric deformation fields to map 3D coordinates from a static canonical space to a deformed state. This allows for the reconstruction of photorealistic scenes and the synthesis of high-fidelity images from camera perspectives not present in the original input data. The framework

DeepLearnToolbox is a research-oriented framework for constructing, training, and optimizing hierarchical neural networks within the Matlab and Octave environments. It provides a modular set of tools for building diverse network topologies, including feedforward, convolutional, and deep belief architectures, using native matrix-based numerical computation. The library distinguishes itself through its support for layer-wise unsupervised pre-training, which establishes initial weights for deep models before supervised fine-tuning. It incorporates stochastic gradient descent and backpropagation

This project is a machine learning educational archive and technical documentation collection. It serves as a deep learning tutorial series and implementation guide, providing theoretical explanations and practical walkthroughs for constructing and optimizing neural networks. The content focuses on the design and construction of diverse model architectures, including convolutional neural networks, Long Short-Term Memory networks, and generative adversarial networks. It details specific implementation patterns for autoencoders, sentiment analysis models, and various classification approaches.