/deep-learning-resources

Repo containing useful deep learning resources for everyone

Deep Learning Resources

Up-to-date repository with useful curated deep learning resources for everyone - from beginner to expert! Feel free to contribute with suggestions!

These resources are organized as follows:

  1. Getting Started in Machine Learning 👶
  2. Getting Started in Deep Learning 💫
  3. Intermediate/Advanced Deep Learning 🤓
  4. Reinforcement Learning 🤖
  5. MLOps ⚙️
  6. Keep up-to-date ⏰
  7. Non-Technical Books 🏖
  8. Community 🤗

Getting Started in Machine Learning 👶

  • Machine Learning Specialization in Coursera from Stanford [online course 👩🏻‍💻]

    In this specialization, Andrew Ng gives a thorough explanation of supervised and unsupervised machine learning algorithms, ranging from linear regression to neural networks and clustering algorithms, perfectly balancing theory with intuition. With this course, you'll gain a strong foundation on machine learning and learn a lot of tips & tricks for applying machine learning in the real world.

Getting Started in Deep Learning 💫

  • Deep Learning Specialization in Coursera from deeplearning.ai [online course 👩🏻‍💻]

    This 5 course specialization teaches how to build and train deep learning models. Once again, Andrew Ng does a great job of introducing you to deep nets and some very important architectures such as CNNs, RNNs, and Transformers.

  • Deep Learning Lecture series by DeepMind x UCL [lectures 👨🏻‍🏫]

    In these 12 lectures, Research Scientists from DeepMind cover a wide variety of very fundamental topics in deep learning.

  • NYU Deep Learning SP21 by Yann LeCun & Alfredo Canziani [lectures 👨🏻‍🏫]

    Here you have the chance to learn from one of the most prominent figures in deep learning - Yann LeCun - also known as one of the three "Godfathers of AI". You can watch Yann LeCunn and Alfredo Canziani's 30 lectures on YouTube taught at New York University.

  • EpyNN [repo 🗄]

    EpyNN is a production-ready but first Educational python resource for Neural Networks. EpyNN is designed for Supervised Machine Learning (SML) approaches by means of Neural Networks.

Intermediate/Advanced Deep Learning 🤓

  • Deep Learning book by Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016) [book 📚]

    If you want to understand every detail of how a system can learn and how deep learning models work then this is the book. This book requires you to be familiar with basic mathematical and machine learning concepts, and if you're not, there are also introductory chapters to help you get started.

  • Generative Adversarial Networks (GANs) Specialization in Coursera from deeplearning.ai [online course 👩🏻‍💻]

    Another great resource from deeplearning.ai for those interested in understanding how GANs work and how you can apply them. Also, you can check the expert panel discussion GANs for Good hosted in celebration of the launch of this specialization.

Reinforcement Learning 🤖

  • Reinforcement Learning in Coursera from University of Alberta [online course 👩🏻‍💻]

    Here you'll have the chance to learn the foundations of Reinforcement Learning and put them into practice through programming assignments. During the course, you'll be able to go through some chapters of the famous Reinforcement Learning book from Richard Sutton and Andrew Barto with the instructors.

  • Reinforcement Learning Lecture Series 2021 by DeepMind x UCL [lectures 👨🏻‍🏫]

    In 13 lectures, DeepMind Researchers go from the basics of RL and planning in sequential decision problems to more advanced topics and modern deep RL algorithms.

  • Reinforcement Learning: an Introduction book by Richard S. Sutton and Andrew G. Barto [book 📚]

    This is the book of Reinforcement Learning, made freely available by the authors. It is used as the base for many RL courses, in particular, the Reinforcement Learning specialization in Coursera, mentioned above.

MLOps ⚙️

  • Machine Learning Engineering for Production in Coursera by deeplearning.ai [online course 👩🏻‍💻]

    MLOps is becoming a very hot topic in AI, along with a more "data-centric" approach, but it is still not a reality in most companies working in AI. This 4 course specialization focuses on the engineering aspect of Machine Learning and has a lot of practical bits of advices and good practices. For a glimpse of the topics being discussed in these courses, check out Andrew Ng's thoughts on MLOps: From Model-centric to Data-centric AI.

  • Full Stack Deep Learning [online course 👩🏻‍💻]

    16 weeks course taught by Sergey Karayev, Josh Tobin, and Pieter Abbeel - all PhDs from UC Berkeley. It is assumed that you are already familiar with the basics of deep learning. The course focuses on the rest of the process of creating production deep learning systems, practical concerns you should have, and what tools you can use.

Keep up-to-date ⏰

  • Lex Fridman Podcast [podcast 🎧]

    Lex's podcast is not only about intelligence but also other interesting topics that can intersect with AI. He has hosted very inspirational and interesting talks.

  • The Robot's Brain podcast by Pieter Abbeel [podcast 🎧]

    Podcast on AI, robotics, and deep learning. Season 2 coming out soon!

  • ML News by Yannic Kilcher [YouTube series 🎥]

    Weekly updates on what's happening in the ML world! (Mondays)

  • The Batch by deeplearning.ai [newsletter 📰]

    Weekly newsletter with some of the week's most interesting developments/news in AI.

  • Practical AI [podcast 🎧]

    Weekly podcasts that cover the latest developments in AI and how you can apply them to your work.

  • AI Coffee Break with Letitia [YouTube series 🎥]

    AI related concepts explained simply - mostly on Natural Language Processing or Computer Vision.

  • The Machine Learning Engineer by The Institute for Ethical AI & ML [newsletter 📰]

    Curated articles, tutorials and blog posts from experienced Machine Learning professionals.

Non-Technical Books 🏖

  • Genius Makers: The Mavericks Who Brought AI to Google, Facebook, and the World by Cade Metz (2021) [book 📚]

    New York Times' reporter narrates the story of how AI changed the world, with the main character being Geoffrey Hinton. The author takes us through the journey of how AI has unfolded since the perceptron, storming past the AI Winter, up until being a game-changer in large companies.

  • The Book of Why by Judea Pearl & Dana Mackenzie (2018) [book 📚]

    "Correlation is not causation". Judea Pearl gives a historical perspective and argues about the importance of causation in science and artificial intelligent systems and how we can derive it.

Community 🤗

  • Deep Learning Sessions Lisboa [community 👥]

    Hey, that's us! 👋🏼 We host meetups where deep learning practitioners can share their experiences, as well as reading groups, where we can all discuss and stay up-to-date with the most recent developments in deep learning.

  • Data Science Portugal [community 👥]

    This community organizes meetups on Data Science and they have an open Slack domain that you can join to stay up-to-date with the latest events in Data Science, job offerings and also meet fellow data scientists.

  • Seminar in Mathematics, Physics & Machine Learning by IST [seminars 🎓]

    Advanced lectures on Machine Learning that you can watch online organized by professors of Instituto Superior Técnico.

  • IST & Unbabel Seminars [seminars 🎓]

    The IST & Unbabel Seminars aim to provide, on a weekly basis, an outlet for discussion of research on Machine Learning and Natural Language Processing by researchers and students all over the world. They are hosted online at 6PM Lisbon Time on Mondays.

  • Weights & Biases Forum [community 👥]

    Community of ML practitioners where you can showcase your work, share ideas, and find collaborators.

  • MLOps Community [community 👥]

    Community of real-world Machine Learning Operations best practices. You can connect to the community through their Slack, check their content on YouTube and Medium, and much more.