DS3010: DS III: Computational Data Intelligence - D-term 2022

Version: Mar 9th, 2022

Tentative Schedule:

-1. Week 1 (3/14 M):

Topic: Overview of Data Science and Class Logistics (Slides)
Readings: N/A

-2. Week 1 (3/17 R):

Topic: Overview of Data Science (Continued!), and Data Collection, Sampling and Measurement(Slides).

-3. Week 2 (3/21 M):

Topic: Data collection and Management (Slides), and Data Analytics using data mining and machine learning (slides)
Note: Project 1 starts.

-4. Week 2 (3/24 R):

Topic: Guest lecture for Python by Siamak.
Topic: Supervised Learning: Regression. (Slides) (updated on 3/25 for fixing the typo on page 18, from "max" to "min")
Reading: Recommended Reading material for regression: M. Jordan, J. Kleinberg, B. Schohop, Pattern Recognition and Machine Learning, Chapter 1.1.

-5. Week 3 (3/28 M):

Topic: Supervised Learning: Regression (Continued!), and Bias and Variance (Slides).
Reading: Recommended Reading material for Bias and Variance: M. Jordan, J. Kleinberg, B. Schohop, Pattern Recognition and Machine Learning, Chapter 3.2.

-6. Week 3 (3/31 R):

Topic: Supervised Learning: Bias and Variance (Continued!), Classification (Slides) (Updated on 4/3).
Note: Project 1 is due.
Note: Project 2 starts.

-7. Week 4 (4/4 M):

Topic: Supervised Learning: Classification: Logistic Regression (Continued), and Multi-layer perceptron/deep Learning (Slides).
Reading: Recommended Reading material for logistic regression: M. Jordan, J. Kleinberg, B. Schohop, Pattern Recognition and Machine Learning, Chapter 4.3.
Reading: Recommended Reading material for Deep Learning/Multi-Layer Perceptron: M. Jordan, J. Kleinberg, B. Schohop, Pattern Recognition and Machine Learning, Chapter 5.1.
Note: Quiz 1 on Canvas (15 mins at the beginning of the class). Topics: Bias and Variance.

-8. Week 4 (4/7 R):

Topic: Supervised Learning: Multi-layer perceptron/Deep Learning (Continued) and Why Deep Learning (Slides).
Reading: Recommended Reading material for Deep Learning/Multi-Layer Perceptron: M. Jordan, J. Kleinberg, B. Schohop, Pattern Recognition and Machine Learning, Chapter 5.1.
Note: Project 1 presentations (two students).

-9. Week 5 (4/11 M):

Topic: Supervised Learning: Why Deep Learning? (Continued); Activation Functions (Slides), Gradient Descent (Slides).
Note: Project 3 starts.
Reading: Recommended Reading material for Deep Learning/Multi-Layer Perceptron: M. Jordan, J. Kleinberg, B. Schohop, Pattern Recognition and Machine Learning, Chapter 5.1.

-10. Week 5 (4/14 R):

Topic: Gradient Descent (continued!); Semi-Supervised Learning (slides).
Reading: Recommended Reading material for Semisupervised Learning: Edited by Olivier Chapelle, Bernhard Schölkopf and Alexander Zien, "Semi-Supervised Learning".
Note: Quiz 2 on Canvas (15 mins at the beginning of the class). Topics: Logistic regression (its limitations) and Logistic regression for multi-class classification.

-11. Week 6 (4/18 M): No Class. Patrios' Day Holiday.
Note: Project 2 is due.

-12. Week 6 (4/21 R):

Topic: Semi-supervised Learning (Continued!), Unsupervised Learning (Slides), Class review (Slides).
Note: Project 2 presentations (two students).

-13. Week 7 (4/25 M):

Topic: Final exam.

-14. Week 7 (4/28 R):

Topic: Transfer Learning (Slides), Ensemble (slides), Reinforcement Learning (slides).

-15. Week 8 (5/2 M):

Topic: Project 3 presentations.
Note: Project 3 is due.