Theory materials

1. Lecture 1: Machine Learning Introduction
   
2. Lecture 2: Probability and Information
   
3. Lecture 3: Linear Algebra & Optimization
   
4. Lecture 4: Linear Regression & Bayesian Linear Regression
   
5. Lecture 5: Perceptron & Logistic Regression
   
6. Lecture 6 (9): Multilayer Perceptrons 
   
7. Lecture 7 (6): Learning theory, Bias-Variance
   
8. Lecture 8 (7): Model Selection
9. Lecture 9 (10): Deep Learning
10. Lecture 10 (11) Convolutional Neural Networks
11. Lecture 11 (12)  Recurrent Neural Networks
    
12. Lecture 12 (13) Autoencoders
13. Lecture 13 (14) Feature Extraction
14. Lecture 14 (8) k Neares Neighbour & Locally Weighted Regession
15. Lecture 15: K-Means Clustering, EM-Clustering (Expectation Maximisation)
16. Lecture 16: PCA, ICA
17. Lecture 17: Decision Trees
18. Lecture 18: Ensemble Methods
19. Lecture 19: Kernel Methods
20. Lecture 20: Support Vector Machines
21. Lecture 21: Bayesian Networks
22. Lecture 22: Stochastic Methods
23. Lecture 23: Applications
24. Lecture 24: Conclusion

Additional materials

• Gradient descent 

  Jupyter Notebook from Hands-On Machine Learning with Scikit_Learn & Tensorflow by Aurélien    Géron with example of convolutional neural networks and transfer learning in Tensorflow (Chapter 13):

• Convolutional Neural Network
  

Practicals

• 1&2 Intro to numpy, scipy and scikit-learn / Probability, Linear Regression, Perceptron, Logistic Regression
  notebook with code
  (Solutions)
• (pen&paper) Probability and Linear Methods (questions, solutions)
• (pen&paper) Backpropagation, solutions
  
• (pen&paper) Learning Theory
  
• (code) Intro to Neural Nets, solutions
• (pen&paper&code) Learning Theory, keras_imdb_rnn.jpynb, biasvariance.ipynb
• (pen&paper)  Non-parametric Learning & Clustering, Step_by_Step_Mathematica.pdf
  
• (pen&paper) PCA, Decision Trees, Solution
• (code) Support Vector Machines, Solution
• (pen&paper) Bayesian Networks

Homeworks

1. pen & paper, solution, grades
2. pen & paper, solution, grades
3. code, solution, grades
4. pen & paper, solution, grades
5. code (longer)

Exam

Grades

• With 2nd exam
• Marks 2nd exam

Attachments

• 1_IN.pdf
• 4_LR.pdf
• 3_LA.pdf
• practical1&2.pdf
• homework1.pdf
• 6_LT.pdf
• practical3questions.pdf
• 9_BP.pdf
• 5_PE.pdf
• Exercises Neural Networks_Students_4.pdf
• 8_NN.pdf
• 10_DL.pdf
• 7_ML.pdf
• loss.pdf
• practical3.pdf
• Exercises Neural Networks_4.pdf
• HM1.pdf
• Exercise 5.pdf
• 11_CN.pdf
• 12_RN.pdf
• 13_AC.pdf
• homework2.sol.pdf
• homework3v02.pdf
• 14_FE.pdf
• HM2_grades.pdf
• exlearningtheory.pdf
• keras_imdb_rnn.ipynb
• exlearningtheory.pdf
• 2_PR.pdf
• 17_DT.pdf
• 18_EN.pdf
• 16_DR.pdf
• homework4.pdf
• practicalnonparametricsolutions.pdf
• 15_CL.pdf
• clustering.nb.pdf
• homework5.pdf
• 19_KE.pdf
• PCA_DT_BN.pdf
• PCA_DT_BN_Solution_8.pdf
• 20_SV.pdf
• 21_BN.pdf
• 22_SM.pdf
• 23_AP.pdf
• 13_convolutional_neural_networks.ipynb.zip
• HM4_5.pdf
• homework4_solution.pdf
• HM1_grades(5).pdf
• 24_CO.pdf
• hw3grades.pdf
• HMgradesHWgroups.pdf
• HMgradesperstudent.pdf
• HMgradesHWgroups.pdf
• 1819Aprendizagem1ep.pdf
• exam20190607_solution_final(6).pdf
• 1examcotacoes.pdf
• 1819Aprendizagem1eprev.pdf
• exam2.pdf
• gradesep2beforerevision.pdf
• exam20190710v2_final_solution.pdf