There are many resources for learning AI/ML, but most of them focus on personal promotion or are biased towards blog posts rather than deep understanding. This article introduces free educational materials that can help you build a deep foundation in AI/ML. Although it is in English, if you use DeepL or automatic script translation, the barrier is not that high. Personally, FastAI was very helpful.
Training Course (VOD)
Fast AI: A well-balanced course with theory, coding, and real-world examples. The entire course and textbook are provided free of charge, and can be run via Jupyter notebooks. Recommended for anyone with Python experience.
Andrey Kapasi's lecture: This lecture is by Andrey Kapasi, a founding member of OpenAI and the head of Tesla's computer vision team. It covers building GPT, deep neural networks, etc. starting from one line of code.
Learning from Data (Caltech Course): A lecture on machine learning theory by Professor Yasser Abu-Mostafa of Caltech. It is better to listen to it before Kafashi's lecture.
Deep Learning: Co-authored with Yoshua Bengio. Provides a deep introduction to deep learning. If you are interested in neural networks, I recommend this book.
≪The Elements of Statistical Learning: The Elements of Statistical Learning>: A textbook that focuses on the theoretical understanding of statistical learning. Suitable for those interested in cutting-edge research labs or companies.
≪Artificial Intelligence: A Modern Approach>: A 1,000-page textbook that covers everything from the basics to statistical learning, machine learning, deep learning, and decision theory.
📚 Welcome to Haebom's archives. --- I post articles related to IT 💻, economy 💰, and humanities 🎭. If you are curious about my thoughts, perspectives or interests, please subscribe. Would you like to be notified when new articles are posted? 🔔 Yes, that means subscribe. haebom@kakao.com
