| MATH80629A | Lectures | Homework | Lab | Project | Office hour

Machine Learning for Large-Scale Data Analysis and Decision Making (MATH80629A): Winter 2022

Hands-on Sessions

Most of the lab materials are in Python using Colab. If you want to create a machine learning model but you don’t have a machine that can take the workload or you don’t want to deal with installing packages and resolving installation issues, Google Colab is a suitable option. Colaboratory is a free Jupyter notebook environment provided by Google where you can use free GPUs and TPUs.

Getting Started

To start working with Colab you first need to log in to your google account, then go to this link. If you are a new Colab user, you can check here to learn more.

Schedule

---

1- Week 1 (January 5): Class introduction and math review

• No hands-on

---

2- Week 2 (January 12): Machine learning fundamentals

• Class summary
• Exercises (colab). If you do not want to use colab, here are the two files you need to download: 1) Fundamentals_questions.ipynb OR Fundamentals_questions.py AND 2) utilities.py
• Solution (colab)

---

3- Week 3 (January 19): Supervised learning algorithms

• Class summary
• Exercises (colab). If you do not want to use colab, here are the two files you need to download: 1) Fundamentals_questions.ipynb OR Fundamentals_questions.py AND 2) utils.py
• Solution (colab)

---

4- Week 4 (January 26): Python for scientific computations and machine learning

• Tutorial (colab)
• Solution (colab)

---

5- Week 5 (February 2): Neural networks and deep learning

• Class summary
• Exercises (colab)
• Solution (colab)

---

6- Week 6 (February 9): Recurrent Neural networks and Convolutional neural networks

• Class summary
• Exercises RNNs (colab)
• Exercises CNNs (colab)
• Solution RNNs (colab)

• Solution CNNs (colab)

• Optional: if you are intrested to learn more, this Exercises CNNs: Pytorch (colab) is an example of CNNs implemented in Pytorch.

---

7- Week 7 (February 16): Unsupervised learning

• Class summary
• Exercises (colab)
• Solution (colab)

---

8- Week 8 (February 23): Reading week

• No hands-on

---

9- Week 9 (March 2): Project meetings

• No hands-on

---

10- Week 10 (March 9): Parallel computational paradigms for large-scale data processing

• Class summary
• Example (colab)

---

11- Week 11 (March 16): Trustworthy Machine Learning

• Class summary

---

12- Week 12 (March 23): Sequential decision making I

• Class summary
• Exercises (colab)
• Solution (colab)

---

13- Week 13 (April 2): Sequential decision making II

• Class summary
• Exercises (colab)
• Solution (colab)

---

14- Week 14 (April 9): Class Project presentation

• Room: TBA

---

15- Week 15 (April 16):

• Final exam: TBA

---