Reading Assignment 1

Introduction to ML and SVM

Write your answers in a PDF and upload the document on Gradescope for submission. The due date is given on Gradescope.

Each question is worth 10 points.

Please watch the videos and slides before answering these questions.

1. See “1.2 Examples of machine learning”. Provide a definition of machine learning. Give an example of “learning from experience E”.
2. Read Section 5.1.1 in Deep Learning, by Goodfellow, Bengio, Courville. Give two examples of tasks.
3. See “1.3 Supervised learning”. What is the primary difference between supervised and unsupervised learning?
4. See “1.3 Supervised learning”. Are the following tasks regression or classification?
   1. diagnose whether a patient has a certain disease based on test result
   2. forecasting temperature
   3. produce a set of control currents for motors in a robot from sensor input
   4. identify the type of a mushroom based on its image
5. See “1.4 Machine learning in engineering”. Give two examples of characteristics that are more important in computational engineering compared to other fields of science.
6. See “1.5 Introduction to SVM”. In the formula $w^T x + b = 0$ to define a hyperplane, $w$ and $b$ are defined up to a constant. How is this constant uniquely set in SVM?
7. See “1.5 Introduction to SVM”. Write down the optimization problem SVM is solving.
8. See “1.5 Introduction to SVM”. Explain what support vectors are.