ISIS AI seminar notes

Schedule

Week	Primary Topic	Description	Coursera Topic	Hands-On ML Book Chapters
1	Overview	Overview, Google Colab, Python Refresher	Week 1	Chapter 1
2	Regression- part 1	Overview, Hands-on Jupyter Notebook	Week 1	Chapter 4
3	Regression - part 2	Quality/performance metrics, Normalization/feature scaling, polynomial regression, logistic regression , decision trees	week 2, week 3	Chapter 2 ,Chapter 6
4	Feature Scaling, Regression Model Evaluation
5	Classification			Chapter 3
6	Neural Networks Learning			Chapter 10
7	Deep Neural Networks			Chapter 11
8	K-means Clustering	Overview of clustering	Lecture 13	Chapter 9
9	Reinforcement Learning			Chapter 18
10	Advance Reinforcement Learning
11	Autoencoders
12	VAE & GAN

📝 References

• Hands-on ML Book
• Hands-on ML Github Repo
• Coursera Machine Learning Course
• Coursera ML Github Repo

Week 1 (4-29-20)

• Week 1 Video Recording Link:

Summary: this week was an introduction to ML. We covered the following topics.

• What is machine learning?
• What are the broad types of machine learning?
• Jupyter notebooks with Google Colab

Reference materials:

• Introduction to ML from Stanford

Homework for the next class:

• Review the Python Refresher
• Review the Jupyter Notebook for Python
• For a more detailed overview of ML, read chapter 1 of the Hands-on ML Book
• Watch the week 1 videos on the Coursera Machine Learning Course

Week 2 (5-6-20):

• Week 2 Video Recording Link

Summary: This week we will cover:

• Regression
• Linear Regression
• Polynomial Regression
• Training Data - Test/Train Split
• Hands-On Activity:
  • Linear Regression
  • Boston Housing Data

Homework and reading for the next class:

• The "Select a Performance Measure" section from chapter 2 of the book.
• The "Feature Scaling" section from chapter 2 of the book.
• The "Multivariate Linear Regression" videos/readings from week 2 of Coursera for understanding polynomial regression.
• The "Classification and Representation" videos/readings from week 3 of Coursera for understanding logistic regression.

Week 4 (5-27-20)

• Week 4 Lecture

Summary: This week we will cover:

• Feature Scaling
  • Normalization
  • Standardization
• Regression Model Evaluation

Week 5 (6-3-20)

• Week 5 Lecture

Summary: This week we will cover:

• Classification
• Encoding
• Different classification methods using Scikit

Week 6

• Week 6 Lecture

Summary: This week we will cover topics around neural networks

Week 7

• Week 7 Lecture

Summary: This week we will cover topics around deep learning and CNN.

Week 8

• Week 8 Lecture

Summary: This week we will cover Clustering and K-means clustering

Week 9

• Week 9 Lecture

Summary: This week we will cover Reinforcement Learning

Week 10:

• Week 10 Lecture

Summary we cover more concepts in Reinforcement Learning

Week 11:

• Week 11 Lecture

Summary: In this lecture we covered the Autoencoders.

Week 12

-Week 12 Lecture

Summary : In this lecture we will cover the Variational Autoencoder(VAE) and Generative Adversarial Networks (GAN)