Schedule #

Important

All deadline and due dates in this course will be at 23:59 EST.

Scroll horizontally to see the full schedule table on mobile devices

Astericks (*) indicate that the lecture slides/notes are available.

Week	Dates	Topics	Homework	Quizzes	Project	Readings
1	Aug 21-25	Course Overview (L1) Data analysis toolbox - P1 (L2)		Q0 - L1,2 (Warmup)		GT Honor Code; [Debugging Common Errors in NumPy](/other/Debugging Common Errors in NumPy.ipynb); Heilmeier catechism; Visual Information Theory by Chris Olah; GitHub Pages; YAML Configuration; NumPy Tutorial; Matplotlib Tutorial; seaborn: statistical data visualization; Overleaf for GT students;
2	Aug 28-Sep 1	Linear Algebra (Notes, L3) Prob and Stats (Notes, L4)		Q1 - L3 & Syllabus Quiz		Correlation vs Covariance; Linear Algebra Review by Zico Kolter;
3	Sep 4-8	Labor Day (Sep 4 - no class for all sections Mon&Tue) Prob and Stats - contd (Notes, L5)	A1 out Sep 5	Q2 - L4,5		The Differences Between Data, Information and Knowledge Cross Entropy as loss function More about Cross Entropy and KLD; Probability Theory Review by Andrew Moore;
4	Sep 11-15	Info Theory (Notes, L6) *Optimization (L7)		Q3 - L6,7	Project team composition due Sep 16	KKT for inequality constrained optimization; Why Cross Entropy over MSE for Classification; Gradient Descent short video; Matplotlib Tutorial; NumPy Tutorial;
5	Sep 18-22	Toolbox - P2 (L8) Clustering & K-Means (*Notes L9)	A1 due Sept-22 A2 out Sept-22	Q4 - L8,9		Curse of dimensionality (Euclidean space example); Jupyter Notbook (Kmeans and DBSCAN);
6	Sep 25-29	GMM - Part 1 (Notes L10) GMM - Part 2 (Notes L11)		Q5 - L10,11		GitHub Student Application
7	Oct 2-6	Hierarchical Clustering (Notes L12) DB SCAN (Notes L13)		Q6 - L12,13	Project proposal due Oct 6 Peer Evaluation Oct 6	Understanding the concept of Hierarchical clustering Technique; Dendrogram Visualization; Jupyter Notbook (Kmeans and DBSCAN);
8	Oct 9-13	Fall Break (Oct 9-10) Clustering Eval (Notes L14)		Q7 - L14
9	Oct 16-20	Density Estimation (Notes L15) Dimension Reduction (Notes L16)	A2 due Oct 20 A3 out Oct 20	Q8 - L15,16		KDE interactive visualization; KDE sampling; KDE SKLearn and sampling; Jupyter Notebook Kernel Density Example; Image reconstruction using PCA; Feature extraction using PCA; PCA for images; PCA as linear combination of features; PCA and Linear Discriminant Analysis;
10	Oct 23-27	Linear Regression (Notes L17) LR contd (Notes L18)		Q9 - L17,18		Simple Linear Regression in Matrix Format; Adding Noise to Regression Predictors;
11	Oct 30-Nov 3	Regularization (Notes L19) NB & Logistic Reg (Notes L20)		Q10 - L19
12	Nov 6-10	NB & Logistic Reg (Notes L21) *Project Practical Advice	A3 due Nov 10 A4 out Nov 10	Q11 - L20,21	Project midpoint report Nov 10 Peer Evaluation Nov 10
13	Nov 13-17	Neural Networks (Notes L23) CNN (Notes L24)		Q12 - L23,24		NN Playground Interactive NN initialization; The role of a hidden layer; Back propagation numerical example; More detailed introduction;
14	Nov 20-24	DT and RF (Notes DT & RF, L25) Student Recess and Thanksgiving break (Nov 22, 23 and 24)		Q13 - L25		CNN Live Demo; A guide to an efficient way to build CNN and optimize its hyper-parameters; Back Propagation in CNN; Transfer learning in CNN; Project Scoring Guidance;
15	Nov 27-Dec 1	SVM - Part 1 (Notes, L26) SVM - Part 2 (Notes, L27)	A4 Due Dec 1	Q14 - L27,28
16	Dec 4-8	SVM-Kernel (Notes, L28) Final Class days (Dec 4-5)			Final Project due Dec 5 Peer Evaluation due Dec 5	KKT and SVM