Coursera Deep Learning Specialisation Lecture Notes

• machine-learning
• computer-science
• course

#course #computer-science #machine-learning

This is a specialisation divided into five courses, and this page serves as the index to all the notes taken in this specialisation. The five courses in this specialisation include:

1. Neural Networks and Deep Learning.
2. Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization.
3. Structuring Machine Learning Projects.
4. Convolutional Neural Networks.
5. Sequence Models.

The course is taught by Andrew Ng, a founder of the Google Brain.

According to Coursera:

If you want to break into AI, this Specialization will help you do so. Deep Learning is one of the most highly sought after skills in tech. We will help you become good at Deep Learning.

In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach.

You will also hear from many top leaders in Deep Learning, who will share with you their personal stories and give you career advice.

AI is transforming multiple industries. After finishing this specialization, you will likely find creative ways to apply it to your work.

We will help you master Deep Learning, understand how to apply it, and build a career in AI.

Most notes are created following the video lectures of this specialisation while some supplemental notes are based on the sources described in the following two sections. Feel free to sue these notes however you want. I am sure that there are many mistakes in these notes so don’t assume everything is correct.

Mahmoud Badry’s open source notebook for this specialisation can be a valuable resource, albeit long and technical. Some my notes are also based on this amazing notebook.

GitHub link dropping

• https://github.com/ashishpatel26/Andrew-NG-Notes
• https://github.com/amanchadha/coursera-deep-learning-specialization
• https://github.com/mbadry1/DeepLearning.ai-Summary

Some other useful resources for learning machine learning

• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: A big book containing lots of detail
• Kaggle: A website by Google with hands-on courses ranging from python to deep learning, along with machine learning competitions
• Grant Sanderson’s Neural Networks playlist
• Neural Networks Demystified by Welch Labs
• Michael Nielsen’s open textbook Neural Networks and Deep Learning

Course 1 - Neural Networks and Deep Learning includes:

• Introduction to machine learning
• Neural networks
• Gradient descent
• Forward propagation
• Cost and loss functions
• Logistic regression
• Vectorisation
• Shallow neural networks
• Activation function
• Deep neural networks
• Hyperparameters

Course 2 - Improving Deep Neural Networks - Hyperparameter Tuning, Regularization and Optimization includes:

• to be continued