Week 2 - Introduction to TensorFlow,Part I

This week you will...

• get a soft introduction to what Machine Learning and Deep Learning are, and how they offer you a new programming paradigm, giving you a new set of tools to open previously unexplored scenarios. All you need to know is some very basic programming skills, and you'll pick the rest up as you go along.

• take the just learned new programming paradigm used in machine learning to the next level by beginning to solve problems of computer vision with just a few lines of code!

Learning Resources

526KB

251030_Introduction_Part_I.pdf

PDF

Open

• Machine Learning Explained in 100 Seconds (Fireship, 2:30 min)

• What is a Loss Function? Understanding How AI Models Learn (IBM Technology, 10 min)

• Backpropagation, intuitively | Deep Learning Chapter 3 (3Blue1Brown, 13 min)

• Parameters vs Hyperparameters (Pankaj Kumar Porwal, 5:40 min)

• Validation data: How it works and why you need it (Galaxy Inferno Codes, 5:40 min)

• TensorFlow Tutorial 3 - Neural Networks with Sequential and Functional API (Aladdin Persson, 21 min)

• TensorFlow Tutorial 14 - Callbacks with Keras and Writing Custom Callbacks (Aladdin Persson, 11 min)

Until next week you should...

• Watch the following videos:

  • Cross Validation (StatQuest Video, 6 min)

    • The video is mandatory

    • The accompanying notebook is optional

  • Bias and Variance (Overfitting) (StatQuest, 7 min)

  • Model Evaluation (Confusion Matrix) (StatQuest, 7 min)

  • Callback Functions in TensorFlow (DigitalSreeni, 10 min)

• Decide on a project for the course and form groups

• Complete the two assignments in the following notebooks:

  • Assignment Notebook 1

  • Assignment Notebook 2