Course Material & Lectures

📖 Course Material

It is in the form of Jupyter Notebook slides with math, code, drawings, plots and explanations

• Slides and material will be uploaded before every lecture on Google Classroom and here.
• Good starting point but but may be not enough.
• Textbooks are required.

Lectures

Opening the Binder link will reproduce the slides live.

• Go forward pressing Space
• Backward with Shift+Space.

Be patient, it takes a while to load Binder. Thanks.

Contributors

• Tommaso Di Mario      

Material

Date	Topic	Slides	Github/HTML	Code/Notebook
	Introduction
Feb 24, 25	Introduction to ML
March 3, 4	The geometry of linear maps
	Unsupervised Learning
March 4, 10	Eigendecomposition, PCA, Intro to 3DMM
March 11,17	3DMM, PCA in High Dimensions, The curse of dimensionality
Mar 18, 24	Clustering, K-means, Visual BoW, Color Compression
March 31	Clustering, Multivariate Gaussian
March 31, April 1	Mixutre of Gaussian, Gaussian Mixture Model
	Non-Parametric, Supervised Learning
April 7, 8	Supervised Learning, k-NN
April 8, 21	Decision Trees, Random Forest
April 13, 14	Easter break
April 22, 28	Model Selection, Evaluation Metrics
	Parametric, Supervised Learning
April 29, May 5	Linear Regression, Gradient Descent, Weight Decay, Basis Functions
May 5, 6	Kernel Methods and SVM
May 12, 13	Perceptron, Logistic Regression, SoftMax
May 18	Neural Nets, MLP, Backpropagation
May 26	Backpropagation with vectors and Jacobians