probml/pml-book

This project is an educational course and machine learning curriculum designed to teach the implementation of neural network architectures and learning algorithms. It provides a structured guide for studying artificial intelligence through a collection of tutorials and practical coding exercises. The curriculum utilizes interactive notebooks that allow for the execution of code within a web browser. This environment enables the prototyping of artificial intelligence models and the analysis of data without requiring a local software installation. The content covers the design and training of

This project is a machine learning curriculum and educational course repository designed as a structured three-month study plan. It provides a guided path for mastering data science and artificial intelligence using the Python programming language. The repository organizes learning materials and code examples to cover mathematics, algorithms, and deep learning fundamentals. It uses a modular curriculum structure to break the domain into discrete monthly and weekly segments. The project functions as a curated resource map that aligns source code and notes with external instructional videos an

Hacker101 is a cybersecurity education platform and web security training portal. It serves as a structured collection of lessons and resources designed to teach students about vulnerability research and penetration testing through guided modules. The platform operates as a static site generator and markdown-based content manager. It uses plain text files with structured metadata to define the hierarchy and properties of educational lessons, transforming this content into pre-rendered HTML files for delivery. The curriculum covers a broad domain of security education, including specialized c

This project is a collection of educational Jupyter Notebooks providing tutorials on neural network construction and tensor operations using the TensorFlow framework. It serves as a machine learning educational repository and implementation guide for deep learning students. The suite focuses on specific advanced architectures, including convolutional networks for image classification, residual networks with skip connections for training stability, and variational autoencoders for generative modeling and data synthesis. It also includes guides for building denoising and deep autoencoders to pe