After finishing this year’s course in Machine Learning, and looking forward to learn more about advanced topics, we have compiled a list of books, blogs and video reccommendations for you. The emphasis here is on conceptual understanding and intuition, rather than technical details or code implementation.
Books
- If you are going to read only one book, let it be Deep Learning, a Visual Approach by Andrew Glassner. We have referenced this book several times in our lectures, and it will help you transition from the basics of Machine Learning to the basic concepts in Deep Learning. In particular it provides a nice introduction to convolutional neural networks (CNNs), a topic that we have not covered in the course, but that is critical for Computer Vision (but see the video reccomendations below!). The part on recurrent neural networks (RNNs) is oriented towards natural language processing (NLP), so will not find many forecasting ideas there. But on the other hand it will introduce you to essential concepts such as embeddings, attention and transformers, which are key to understand the current state of the art in NLP but also in forecasting.
Videos
- As for Convolutional Neural Networks, you can not probably get much better than A friendly introduction to Convolutional Neural Networks and Image Recognition by Luis Serrano. In little over 30 minutes Luis will provide you with a good intuition about the central points of CNNs and the essential lingo you need to understand the topic. This is a must watch! After you finish it you can go to Glassner’s book (see above) to get a more in-depth understanding of the topic.