CS231n is a course that introduces Convolutional Neural Network for Visual Recognition. I found this class very helpful in machine learning, especially deep learning. It introduces state-of-the-art technique in computer vision.
You will build up your own network from scratch with Python in the assignments. Also, you will be working in either TensorFlow or PyTorch, two popular and powerful deep learning frameworks.
The datasets in assginment 3 is pretty large. Try Download youself. (get_assignment3_data.sh)
✅Q1: Image Captioning with Vanilla RNNs
✅Q2: Image Captioning with LSTMs
✅Q3: Network Visualization: Saliency maps, Class Visualization, and Fooling Images
✅Q4: Style Transfer
✅Q5: Generative Adversarial Networks
Material: http://cs231n.github.io/
YouTube: Stanford University School of Engineering or Andrej Karpathy
There is another Machine Learning course I HIGHLY recommend 👍
Intro to machine learning on Udacity, lectured by Sebastian Thrun and Katie Malone.