Awesome GitHub RepositoriesModel Selection and Validation

Scikit-learn is a machine learning library for predictive data analysis that provides a collection of algorithms for supervised and unsupervised learning. It functions as a comprehensive toolkit for data preprocessing, dimensionality reduction, and model selection, allowing users to classify data objects, predict continuous values, and cluster similar items based on historical patterns. The project is defined by a unified interface design where objects either learn from data, transform data, or chain these operations into sequential workflows. To ensure performance on large or high-dimensiona

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

This project is a comprehensive deep learning framework and educational platform designed for constructing, training, and evaluating neural network architectures. It provides a modular environment for building models through tensor operations and automatic differentiation, supporting a wide range of tasks from image classification and object detection to sequential data processing. Beyond its core technical capabilities, the project distinguishes itself by integrating professional career development resources directly into its learning ecosystem. It offers structured guidance, resume reviews,

Vercel is a cloud platform for building, deploying, and scaling web applications. It provides a unified infrastructure that automates the build process by detecting project frameworks and distributing static and dynamic content through a global content delivery network. The platform executes application logic using serverless functions that scale automatically based on real-time traffic demand. The platform distinguishes itself through a centralized AI gateway that proxies requests to multiple model providers, enabling standardized authentication, observability, and cost tracking. It supports

Ai-Learn is an educational repository and technical reference designed to facilitate the mastery of artificial intelligence and data science workflows. It provides a structured curriculum that combines theoretical mathematical foundations with practical coding exercises, enabling users to build predictive models, neural networks, and analytical pipelines using Python. The project distinguishes itself by emphasizing a first-principles approach to machine learning. Rather than relying solely on high-level abstractions, it guides users through the reconstruction of core algorithms from scratch,

sktime is a machine learning framework designed for time series analysis. It provides a unified interface for performing time series forecasting, classification, and anomaly detection, integrating these capabilities into a standardized toolkit compatible with the scikit-learn API. The framework allows for the construction of complex analysis workflows through model pipelining and ensemble-based aggregation. It uses adapter-based integration to wrap external time series libraries, providing a single entry point for diverse algorithmic implementations. Its capabilities cover temporal data tran

This project is a comprehensive machine learning interview guide and technical study resource designed for individuals preparing for machine learning and AI engineering roles. It provides a collection of materials and practice problems covering core algorithms, theoretical fundamentals, and the implementation of neural network architectures. The resource serves as a technical reference for generative AI development, focusing on the design and optimization of large language models and diffusion systems. It includes frameworks for system design, covering the architecture of production machine l

Este proyecto es un recurso educativo integral y manual técnico centrado en el machine learning interpretable y la IA explicable. Sirve como libro de texto y referencia para implementar técnicas que hacen que los modelos de machine learning complejos sean transparentes y comprensibles para los humanos. El recurso proporciona orientación tanto sobre la construcción de modelos inherentemente transparentes, como árboles de decisión y modelos lineales dispersos, como sobre la aplicación de métodos de explicación post-hoc a sistemas de caja negra. Detalla metodologías específicas para cuantificar la importancia de las características, generar fundamentos para predicciones individuales y utilizar modelos sustitutos para aproximar procesos complejos de toma de decisiones. El contenido cubre una amplia gama de capacidades analíticas, incluyendo el análisis de influencia de características globales y locales, la interpretabilidad de visión artificial y el uso de contribuciones de teoría de juegos como los valores de Shapley. También aborda la evaluación de modelos mediante evaluaciones de interpretabilidad, flujos de trabajo de depuración para identificar atajos de modelos y el diseño de estructuras de algoritmos transparentes. El proyecto se implementa como una colección de Jupyter Notebooks.

Yellowbrick es una librería de visualización de machine learning y herramienta de diagnóstico de modelos diseñada para analizar la importancia de las características, distribuciones objetivo y métricas de error del modelo. Sirve como un kit de herramientas visual para diagnosticar el subajuste (underfitting) y sobreajuste (overfitting) mediante el uso de curvas de validación y aprendizaje. El proyecto proporciona suites especializadas para evaluar modelos predictivos y aprendizaje no supervisado. Permite la determinación de conteos de clústeres óptimos mediante métodos de codo y coeficientes de silueta, y evalúa la calidad de clasificadores y regresores a través de curvas ROC, matrices de confusión y gráficos de residuos. La librería cubre varias áreas de capacidad de alto nivel, incluyendo análisis de ingeniería de características para identificar variables predictivas, ajuste de hiperparámetros para ajustar la complejidad del modelo y diagnóstico de errores de regresión para identificar puntos de datos influyentes. También incluye herramientas para proyección de aprendizaje de variedades (manifold learning) para visualizar datos de alta dimensión y corpus de texto. La herramienta se integra con la API de Scikit-Learn para consumir métodos estándar de fit y predict.