Date | Reading | Topic | Assignments | |
---|---|---|---|---|
1 | Aug 21 | Intro and Motivation | Read syllabus/schedule | |
2 | Aug 23 | 1, 2.1, 3.1-3.3 | Perceptron and Delta Rule | Install toolkit (before class) |
3 | Aug 28 | 3.4 | Perceptron and Delta Rule | Perceptron HW (before class) |
4 | Aug 30 | 2.2 Perceptron Lab description | Data, Testing, and ML Toolkit | Quadric Machine HW (before class) |
5 | Sep 4 | 3.5 Logistic Regression | Linear Regression and Logistic Regression | |
6 | Sep 6 | 2.4-2.5 Group Project proposal description | Inductive Bias | Linear Regression HW (before class) Logistic Regression HW (before class) |
7 | Sep 11 | 4.1-4.3 | Backpropagation | Perceptron Lab (due by 11 pm) |
8 | Sep 13 | 4.4-4.5 Experiment with TensorFlow playground Backpropagation Lab description | Backpropagation | Backpropagation HW (before class) |
9 | Sep 18 | 4.6 | Backpropagation | |
10 | Sep 20 | 2.2 | Comparing Classifiers, Grad School | Group Project Proposal |
11 | Sep 25 | 6.1 Optional: Data Preparation | Feature Selection and Reduction | |
12 | Sep 27 | 6.2,6.5-6.6 Optional: 6.3-6.4 | Features (cont), PCA | Group Project Voting |
13 | Oct 2 | 12.1-12.2 | Decision Trees | Backpropagation Lab (due by 11 pm) Begin gathering data for group project |
14 | Oct 4 | 12.3-12.4 Decision Tree Lab description | Decision Trees | Decision Tree HW (before class) Data gathering report |
15 | Oct 9 | Midterm | ||
16 | Oct 11 | 5.1-5.2,7-7.2.1 Nearest Neighbor Lab description | Nearest Neighbor | |
17 | Oct 16 | 2.3 | Bayesian Learning | k-Nearest Neighbor HW (before class) |
18 | Oct 18 | 7.2.2-7.2.3 Optional: 5.3 | Radial Basis Function Networks, Data Mining | Naïve Bayes HW (before class) |
19 | Oct 23 | 13 | Ensembles | Decision Tree Lab (due by 11 pm) |
20 | Oct 25 | 14.1 Section 5.4 of this reading | Clustering and Unsupervised Learning | Group Project Progress Report |
21 | Oct 30 | 14.2-14.3 Clustering Lab description | Clustering and Unsupervised Learning | HAC HW (before class) |
22 | Nov 1 | 10.1-10.4 | Genetic Algorithms | Nearest Neighbor Lab (due by 11 pm) k-Means HW (before class) |
23 | Nov 6 | 11.1-11.3 | Markov Models | |
24 | Nov 8 | 16.3 | Hidden Markov Models | |
25 | Nov 13 | 11.4-11.7 | Reinforcement Learning and Q-Learning | Clustering Lab (due by 11 pm) |
26 | Nov 15 | Group Project Time | RL HW (before class) | |
27 | Nov 27 | 8.1-8.3 | SVMs | |
28 | Nov 29 | Final Exam Review | Group Project Report (due by 11 pm) | |
29 | Dec 4 | Group Project Oral Presentations:
| ||
29 | Dec 6 | Group Project Oral Presentations:
| ||
30 | Dec 14 | Final (10:00am) |
The schedule is subject to change. The final is Friday, December 14 from 10:00am to 12:00pm in our normal classroom. The final is comprehensive.