Python is the main programming language used in the development of machine learning models.

The fundamental principles of machine learning remain unchanged, so focus specifically on lectures 1 through 5 and 11 through 13.

"Speech and Language Processing" textbook by Dan Jurafsky and James H. Martin is the Bible of NLP. Focus on Part 1.

The main model architecture used in text and image processing nowadays is transformer architecture.  Python library for working with it is called transformers and can be found in the HuggingFace.co hub.

A course on deep learning for CV; good for getting a sense of the fundamentals.

PyTorch is a widely used machine learning framework, based on Python.

Deep learning is what makes AI possible. Once you've gained some skill with PyTorch, check out this interactive textbook on DL.

Word embeddings are a prerequisite for any machine learning performed over text. This is a practical implementation of the word2vec algorithm you learn about in Chapter 15 of the textbook above. 

This repository by Andrej Karpathy is a great practical introduction to the workings of generative language models.

The Deep Learning 1 course covers key concepts in recent CV research like ResNet, adversarial attacks and vision transformers.