Slides

• T0 Course Organization
  
• T1 Machine Learning, Univariate Data Analysis (and lecture notes)
• T2 Associative Learning: Decision Trees
  
• T3 Evaluation Part I
  
• T4 Bayesian Learning v2
  
• T5 Lazy Learning
  
• T6 Regression v2
  
• T7 Evaluation Part II (updated link)
  
• T8 Perceptron, Gradient Descent
  
• T9 Neural Processing
• T10 Deep Learning
  
• T11 Clustering
• T12 Dimensionality Reduction

Short video tutorials

• Playlist: https://www.youtube.com/playlist?list=PLib7yVWFcU8Iq6pSFJ5Z_N6zWmugcduGl
  

Notes

• T1 slide 28: consider descriptive (and predictive) instead of unsupervised (and supervised)
  
• T4: version 2 corrects typo in slides 13 and 20
• T6: slide 35 removed, typo corrected in slide 23
  
• (new) T6 slide 24: exp(-1) is the correct answer for the Euclidean norm; exp(-2) is achieved using the l1/Manhattan norm
• T7: contents for exam only until slide 14
  
• (new) T9 slide 33: "a2b4" should be replaced by "a4b4"; slides 49-50 assumes softmax on the last layer, slide 50 𝛅^[𝑝]𝐱^𝑇should be 𝛅^[𝑝]𝐱^[p-1]𝑇
  
• T11 slide 34: you can assume the same multinomial distribution u_k for y1 and y2 with u_k being the distribution of cluster c_k
  
• Data profiling examples and Gaussian programming facilities in this notebook (and accompanying data)