Contact: hugomcp@di.ubi.pt

 

Machine Learning (Aprendizagem Automática) (MEI)

2019/2020

 

 


 

News


  • 09/7/2020: The "Classificação-Aprendizagem" marks are available.


  • 06/7/2020: 06/7/2020: The individual presentations/discussions of the works carried out in the scope of the course have been scheduled.
Each student should connect by Skype to "hugomcp_skype", share his screen and have the audio + video enabled. Students should be able to justify
all the decisions in the cope of the fifth practical project (and eventually in the remaining ones too).


 
Aluno Nome App.
E10211 Guilherme AntÛnio Carrilho Catal„o  N/A
E10331 Wagner Ruben Gaspar Benjamim  N/A
E10336 Daniel Afonso Valente  4ª fª, 08/07, 14:00-14:20
E10360 Edgar Daniel Santos de Jesus  4ª fª, 08/07, 14:20-14:40
E10528 AntÛnio JosÈ Marques Abreu  4ª fª, 08/07, 14:40-15:00
M8327 Eduardo Xavier Santos  N/A
M9284 Atungulu Kabakaba  -
M9653 Diandre de Paula Cavalini  4ª fª, 08/07, 15:00-15:20
M9671 Pedro Miguel Ferreira de Oliveira  5ª fª, 09/07, 17:40-18:00
M9672 Joana Cabral Amaral Nunes da Costa  4ª fª, 08/07, 15:40-16:00
M9674 Daniel Nascimento Fernandes  N/A
M9675 Alexandre Daniel Ramos Fonseca  4ª fª, 08/07, 16:00-16:20
M9681 Carolina Galv„o Lopes  4ª fª, 08/07, 16:20-16:40
M9722 Pedro Miguel Rolo da Silva  4ª fª, 08/07, 16:40-17:00
M9725 Ariel Carvalho de Jesus  N/A
M9846 Francisco Jaime Chimbinde  N/A
M9855 Mariana Magalh„es Dantas  4ª fª, 08/07, 17:00-17:20
M9933 Rita Pessoa Correia  5ª fª, 09/07, 17:20-17:40
M9943 Bruno Rodrigues Pereira  N/A
M9984 Jo„o Pedro da Cruz Brito  4ª fª, 08/07, 17:40-18:00
M9988 Tom·s Francisco Nogueira das Neves Marques JerÛnimo  5ª fª, 09/07, 14:00-14:20
M10071 Jo„o Pedro Monteiro Fernandes  5ª fª, 09/07, 14:20-14:40
M10110 JosÈ Nuno Rocha Lamar„o  5ª fª, 09/07, 14:40-15:00
M10114 Eduardo Rodrigues de Almeida  5ª fª, 09/07, 15:00-15:20
M10122 Jose Fali Jau  N/A
M10137 Jo„o Duarte Baptista Marques  5ª fª, 09/07, 15:20-15:40
M10156 LuÌs Carlos Cavaca Pereira  5ª fª, 09/07, 15:40-16:00
M10157 AndrÈ Ribeiro Martins  5ª fª, 09/07, 16:00-16:20
M10259 Ricardo Mendes Domingos  5ª fª, 09/07, 16:20-16:40
M10278 Muhammad Luqman Jamil  5ª fª, 09/07, 16:40-17:00
M10304 Cristiano Pires PatrÌcio  5ª fª, 09/07, 17:00-17:20



  • 20/5/2020: The due date for delivering the Reinforcement Learning practical project was postponed to June, 5th, 23:59.
  • 18/5/2020: TULA Labs. is sponsoring (798€/month x 10 months) one M.Sc. dissertation for 2020/21 in the scope of "Machine Learning/Computer Vision 
       Solutions for Autonomous Navigation Vehicles". All the details can be found [here]. In case of being interested, please contact hugomcp@di.ubi.pt ASAP.
  • 05/5/2020: The description of the extra practical project is available below.
  • 26/4/2020: A "Zoom" meeting for the Machine Learning class is scheduled to May 5th, 2020, at 11:00.
    Students should join using the ID: 443-1810-365.
  • 26/4/2020: The due date for delivery the third practical project was postponed to May 18th.
  • 17/3/2020: The description of the second practical project is already available
  • 14/3/2020: The March, 17th classes and exercises will be available as a "MS PowerPoint" presentation on March 17th, at 11:00.  

  • For any doubts, the teacher will be available from 14:00-15:00 at the following skype address: "hugomcp_skype"

  • 13/3/2020: Due to the COVID-19 pandemic virus, no presential classes will be lectured up to (at least) April, 13th!

  • For any doubts, the teacher will be available from 14:00-15:00 at the following skype address: "hugomcp_skype"

  • 17/2/2020: The important information about the course is available at the website;



Evaluation Criteria

  • Assiduity (A)
    • Approving the course requires a minimum assiduity level of 80% in theoretical and practical classes.
  • Practical Projects (P)
    • The practical projects weight 10 points for the final classification;
    • In order to get approved, at least 5 points (out of 10) should be obtained in the sum of all practical projects;
      • Part 1: Linear Regression (2.5 points): due date March, 16th, 23:59, by email.
      • Part 2: Logistic Regression (2.5 points): due date April, 13th, 23:59, by email.
      • Part 3: Clustering (2.5 points): due date May, 18th, 23:59, by email.
      • Part 4: Reinforcement Learning (2.5 points): due date June, 5th, 23:59, by email.
  • Written Test
    • Test (F1) - Tuesday, June, 2nd, 09:00-11:00, Room 6.18 
(Due to the COVID lock down, this test was replaced by an extraordinary practical project + an individual presentation)
  • Classification (Teaching-Learning period)
    • C=P*10/20+F*10/20
  • Admission to Exams
    • All students that get at least 6 points in the "Teaching-Learning" period are admitted to exams.
  • Exams
    • The practical projects marks are also considered to all the exams.

Program

1) Introduction;

2) Model Representation, Linear regression;

3) Logistic Regresion;

4) Dimensionality Reduction;

5) Neural Networks;

6) Support Vector Machines;

7) Unsupervised Classification;

8) Density Estimation;

9) Reinforcement Learning;


Bibliography

  • Main
    • C. Bishop. Pattern Recognition and Machine Learning, Springer, ISBN-13: 978-0387310732, 2011.

  • Secundary

 

    • M. Mohri, A. Rostamizadeh, A. Talwalkar, F. Bach. Foundations of Machine Learning,  ISBN-13: 978-0262039406, 2018.

 


Aulas

Semana

Theoretical

Practical

Class 18/02


[Class 1]

[Python Introduction]

Class 25/02

(Carnival)


Class 03/03

[Class 2] [Practical Sheet 2] [pizza.csv]
[linear_regression.py]

Class 10/03

(Cont.)


Class 17/03

[Class 3]
[Presentation Class 3]
[wines.csv] [Solution_Logistic_regression.py]

Class 24/03

[Class 4]
[Presentation Class 4]

[Practical Project 2 Description]

Class 31/03

[Class 5]
[Presentation Class 5]

[AR.csv] [AR.tar]

Class 14/04

[Class 6]
[Presentation Class 6]

[PCA.py]

Class 21/04

[Class 7]
[Presentation Class 7]

[PCA vs LDA.py]

Class 28/04

[Class 8]
[Presentation Class 8]

[NN.py]

Class 05/05

[Class 9]
[Presentation Class 9]

[Practical Project 3 Description]
[Practical Project 5 Description]

Class 12/05

[Class 10]
[Presentation Class 10]

[Deep Learning.py]
 

Class 19/05

[Class 11]
[Presentation Class 11]
[Presentation Class 11 (cont)]


Class 26/05

[Class 12]
[Presentation Class 12]
[Practical Project 4 Description]

Class 02/06

 


 


Marks


Aluno Nome FINAL
E10211 Guilherme AntÛnio Carrilho Catal„o  4
E10331 Wagner Ruben Gaspar Benjamim  3
E10336 Daniel Afonso Valente  12
E10360 Edgar Daniel Santos de Jesus  11
E10528 AntÛnio JosÈ Marques Abreu  5
M8327 Eduardo Xavier Santos  3
M9284 Atungulu Kabakaba  10
M9653 Diandre de Paula Cavalini  15
M9671 Pedro Miguel Ferreira de Oliveira  14
M9672 Joana Cabral Amaral Nunes da Costa  15
M9674 Daniel Nascimento Fernandes  3
M9675 Alexandre Daniel Ramos Fonseca  17
M9681 Carolina Galv„o Lopes  15
M9722 Pedro Miguel Rolo da Silva  11
M9725 Ariel Carvalho de Jesus  3
M9846 Francisco Jaime Chimbinde  3
M9855 Mariana Magalh„es Dantas  15
M9933 Rita Pessoa Correia  17
M9943 Bruno Rodrigues Pereira  3
M9984 Jo„o Pedro da Cruz Brito  18
M9988 Tom·s Francisco Nogueira das Neves Marques JerÛnimo  15
M10071 Jo„o Pedro Monteiro Fernandes  13
M10110 JosÈ Nuno Rocha Lamar„o  12
M10114 Eduardo Rodrigues de Almeida  14
M10122 Jose Fali Jau  3
M10137 Jo„o Duarte Baptista Marques  14
M10156 LuÌs Carlos Cavaca Pereira  13
M10157 AndrÈ Ribeiro Martins  12
M10259 Ricardo Mendes Domingos  14
M10278 Muhammad Luqman Jamil  10
M10304 Cristiano Pires PatrÌcio  19