Awesome deep learning
A curated list of awesome deep learning tutorials, projects, and communities.
What is Awesome deep learning?
Awesome Deep Learning is a curated GitHub repository that aggregates high-quality resources for learning and practicing deep learning. It provides structured lists of books, courses, videos, research papers, tutorials, datasets, frameworks, and tools, serving as a one-stop reference for the deep learning community.
Students, researchers, data scientists, and developers seeking organized learning materials, state-of-the-art research references, and practical tools for deep learning projects.
It saves time by vetting and categorizing the best resources from across the web, maintained by the community to ensure relevance and quality, unlike scattered blog posts or unverified content.
Overview
A curated list of awesome Deep Learning tutorials, projects and communities.
Use Cases
Best For
- Students looking for structured deep learning courses and textbooks
- Researchers seeking seminal papers and conference information
- Practitioners needing datasets and frameworks for projects
- Newcomers exploring introductory tutorials and video lectures
- Developers comparing tools like TensorFlow, PyTorch, and Keras
- Educators compiling reading lists or course materials
Not Ideal For
- Experienced researchers needing the latest, unpublished preprints
- Teams building production systems who require version-specific documentation and support
- Learners preferring interactive, gamified platforms over static reading lists
Pros & Cons
Pros
Aggregates hundreds of books, courses, and datasets in one place, such as over 20 books and 40 courses listed, saving users from scattered searches.
Maintained by contributors who vet entries, ensuring resources like seminal papers from Bengio and Hinton are included.
Organized into clear sections like Frameworks, Datasets, and Tutorials, mirroring the Table of Contents for easy navigation.
Includes extensive lists of frameworks and tools, from TensorFlow and PyTorch to newer ones like JAX, aiding technology selection.
Cons
Relies on external URLs that can break over time, such as older course links from 2010-2014, without a built-in maintenance system.
Lists resources without ratings or reviews, so beginners might struggle to choose between options like multiple machine learning courses.
Lacks features like search, personalized recommendations, or hands-on exercises, unlike platforms like Coursera or Kaggle.
Frequently Asked Questions
Related Projects
Open Source Society University🎓 Path to a free self-taught education in Computer Science!
Awesome machine learningA curated list of awesome Machine Learning frameworks, libraries and software.
University Courses:books: List of awesome university courses for learning Computer Science!
Data Science:memo: An awesome Data Science repository to learn and apply for real world problems.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.