This is a repository to organize the teaching material for Statistical Machine Learning (ETC3555), to be taught by Souhaib Ben Taieb. The tutorial will be supervised by Cameron Roach.

• Moodle (for discussion forum, assignments, grades, protected material)

1. Lectures
   1. Tuesday 9am-10am at CL_20 Chancellors Walk, Room E365, East Level 3 (Bldg 11)
   2. Wednesday 10am-11am at CL_20 Chancellors Walk, Room E365, East Level 3 (Bldg 11)
2. Labs
   1. Wednesday 12:30-14:00 at CL_20 Chancellors Walk, Room S317 Computer Lab (Building 11)

• Souhaib: Friday, 26 October, 3pm-5pm, Room E759, Menzies Building, Clayton campus
• Cameron: Monday, 22 October, 10am-11:30am, Room W11.06, Menzies Building, Clayton campus

• Souhaib: Tuesday, 10am-11am, Room E759, Menzies Building, Clayton campus
• Cameron: Wednesday 9am-10am, Room W11.06, Menzies Building, Clayton campus

• Exam (60%)
• Project (20%)
• 5 assignments (20%, 4% each)

• Project 2018

Oct 16, Tuesday, 9:00am, CL_20 Chancellors Walk, Room E365, East Level 3 (Bldg 11)

1. 09:00 am - Group 1: PAUL GORDON HENDY and JACK GRAHAM DAVIES (Reinforcement learning)
2. 09:12 am - Group 2: ELIZAVETA MAKSIMOVNA KOSHENKO and ADYE ROHAN DOUGLAS (t-SNE)
3. 09:24 am - Group 3: JIANXIANG ZHENG and KAMALPREET SINGH (Convolutional Neural Networks)
4. 09:36 am - Group 4: WILLIAM CHAN and JENNIFER HE (DBSCAN)

Oct 17, Wednesday, 10:00am, CL_20 Chancellors Walk, Room E365, East Level 3 (Bldg 11)

5. 10:00 am - Group 5: XIN QIAN ENG and HONG XIANG YUE (EM algorithm)
6. 10:12 am - Group 6: HAN YANG LIM and MITCHELL RYAN ONG-THOMSON (Boosting)
7. 10:24 am - Group 7: ZEZHENG ZHANG and JIAYIN TANG (Recurrent Neural Networks)
8. 10:36 am - Group 8: MICHAEL SEN JIE CHAN and BENJAMIN GORMLY CRAINE (Gaussian mixture methods)
9. 10:48 am - Group 9: JIAYING WU (Self-organizing map)

• Week 1. Introduction

  • Lecture 1 (Jul. 24): Introduction [slides]
  • Lecture 2 (Jul. 25): The learning problem [slides]
  • Lab 1: Introduction to the R Tidyverse I [lab 1 (pdf)] [lab 1 (Rmd)] [lab 1 solutions (pdf)] [lab 1 solutions (Rmd)]

• Week 2. The learning problem

  • Lecture 3 (Jul. 31): The learning problem [slides]
  • Lecture 4 (Aug. 1): The learning problem [slides]
  • Lab 2: Introduction to the R Tidyverse II [lab 2 (pdf)] [lab 2 (Rmd)] [lab 2 solutions (pdf)] [lab 2 solutions (Rmd)]

• Week 3. Linear models

  • Lecture 5 (Aug. 7): The learning problem [slides]
  • Lecture 6 (Aug. 8): Linear models [slides]
  • Lab 3 + assignment 1 (due Aug. 12): The learning problem [lab 3 (pdf)] [lab 3 (Rmd)] [lab 3 solutions (pdf)] [lab 3 solutions (Rmd)]

• Week 4. Gradient descent

  • Lecture 7 (Aug. 14): Gradient descent [slides]
  • Lecture 8 (Aug. 15): Stochastic gradient descent [slides]
  • Lab 4: Linear models and gradient descent (with Souhaib) [lab 4 (pdf)]

• Week 5. Neural networks

  • Lecture 9 (Aug. 21): Neural networks [slides]
  • Lecture 10 (Aug. 22): Neural networks [slides]
  • Lab 5 + assignment 2 (due Aug. 28): Linear models and gradient descent (with Souhaib) [lab 5 (pdf)] [lab 5 (Rmd)] [lab 5 solutions (pdf)] [lab 5 solutions (Rmd)]

• Week 6. Neural networks

  • Lecture 11 (Aug. 28): Backpropagation [slides]
  • Lecture 12 (Aug. 29): Backpropagation [slides]
  • Lab 6: Neural networks and backpropagation [lab 6 (pdf)] [lab 6 (Rmd)] [digits.Rdata] [weights.Rdata ] [plotDigits.R] [lab 6 solutions (pdf)] [lab 6 solutions (Rmd)]

• Week 7. Deep neural networks

  • Lecture 13 (Sep. 4): Deep neural networks [slides]
  • Lecture 14 (Sep. 5): Deep neural networks [slides]
  • Lab 7 + assignment 3 (due Sep. 16): Deep neural networks [lab 7 (pdf)] [lab 7 (Rmd)] [lab 7 solutions (pdf)] [lab 7 solutions (Rmd)]

• Week 8. Supper Vector Machines (SVM)

  • Lecture 15 (Sep. 11): Supper Vector Machines [slides]
  • Lecture 16 (Sep. 12): Supper Vector Machines [slides]
  • Lab 8: SVM [lab 8 (pdf)] [lab 8 (Rmd)]

• Week 9. Recommender systems and matrix completion

  • Lecture 17 (Sep. 18): See videos below
  • Lecture 18 (Sep. 19): See videos below
  • Lab 9 + assignment 4: Recommender systems and matrix completion [lab 9 (zip)] [lab 9 solutions (pdf)] [lab 9 solutions (Rmd)]
  • Lecture 16.1 — Recommender Systems | Problem Formulation — [ Machine Learning | Andrew Ng ]: https://www.youtube.com/watch?v=giIXNoiqO_U
  • Lecture 16.2 — Recommender Systems | Content Based Recommendations — [ Andrew Ng ]: https://www.youtube.com/watch?v=9siFuMMHNIA
  • Lecture 16.3 — Recommender Systems | Collaborative Filtering — [ Machine Learning | Andrew Ng ]: https://www.youtube.com/watch?v=9AP-DgFBNP4
  • Lecture 16.4 — Recommender Systems | Collaborative Filtering Algorithm — [ Andrew Ng ]: https://www.youtube.com/watch?v=YW2b8La2ICo
  • Lecture 16.5 — Recommender Systems | Vectorization Low Rank Matrix Factorization — [ Andrew Ng ]: https://www.youtube.com/watch?v=5R1xOJOFRzs
  • Lecture 16.6 — Recommender Systems | Implementational Detail Mean Normalization — [ Andrew Ng ]: https://www.youtube.com/watch?v=Am9fhp2Q91o

• Semester break

• Week 10. Text mining

  • Lecture 19 (Oct. 2): Text mining [slides]
  • Lecture 20 (Oct. 3): Text mining [slides]
  • Lab 10: Text mining [lab 10 (pdf)]

• Week 11. Text mining

  • Lecture 21 (Oct. 9): Text mining
  • Lecture 22 (Oct. 10): Revision
  • Lab 11 + assignment 5: Text mining [lab 11 (pdf)] [lab 11 (Rmd)]

• Week 12. Project presentation

  • Lecture 23 (Oct. 16): Project presentation (I/II)
  • Lecture 24 (Oct. 17): Project presentation (II/II)
  • No lab.