Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2. 

Source: from the Support Vector Machines chapter, here

Content

• The machine learning landscape
• End to end machine learning project
• Classification
• Training linear models
• Support vector machines
• Decision trees
• Ensemble learning and random forests
• Dimensionality reduction
• Unsupervised learning
• Neural nets with Keras
• Training deep neural networks
• Custom models and training with Tensorflow
• Loading and preprocessing data
• Deep computer vision with CNNs
• Processing sequences using rnns and CNNs
• NLP with rnns and attention
• Autoencoders and GANs
• Reinforcement learning
• Training and deploying at scale

You can access this material here. For other free tutorials (including from Berkeley, Harvard, Columbia, Google, Microsoft and so on), follow this link.