Notes, demos and materials for learning Machine Learning

In addition to the material in this git repository, I've also used materials from my computer vision, data mining and deep learning modules. Please feel free to take a look at the lecture slides and notes for these which can be found here:

• http://comp3204.ecs.soton.ac.uk / https://github.com/jonhare/COMP3204
• http://comp6237.ecs.soton.ac.uk / https://github.com/jonhare/COMP6237
• http://comp6248.ecs.soton.ac.uk / https://github.com/jonhare/COMP6248

(Note that this is only a guide. We'll adapt the content to your needs during the course.)

• Monday 27th July 2020: Overview of Machine Learning

  • Leaders: Prof Niranjan, Prof Prugel-Bennett and Dr Hare
  • 10:00-11:30
    • Introductions: Course teachers and students
    • Playing with zoom
    • ML in one page Niranjan
    • Artificial Idiots Adam
    • Failures of machine learning Jon
  • 11:30-12:00
    • Coffee
    • Chat in Break out rooms
  • 12:00-1:00 Niranjan
    • Understanding simple machine learning algorithms
      • Linear models, Gaussian distributions
  • 1:00-2:00
    • Lunch (exercise)
  • 2:00-3:30 Niranjan
    • Bayes Optimal Regression
    • Fisher Discriminant Analysis
    • Peceptron
  • 3:30:4:00
    • Coffee (break out rooms)
  • 4:00-5:00 Jon
    • Hands-of practical session
    • Introduction to python, scikit-learn and CoLab

• Tuesday 28th July 2020: Introduction to Machine Learning

  • 9:30-11:00 Jon
    • More practicals/exercises
  • 11:00-11:30
    • Coffee/break out rooms
  • 11:30-1:00 Jon
    • Handling Data
  • 1:00-2:00
    • Lunch
  • 2:00-3:30 Niranjan
    • Feature selection and Lasso
    • MLPs
    • Gradient learning, SGD, momentum
  • 3:30-4:00
    • Coffee
  • 4:00-5:00
    • Evaluating performance
      • ROC curves
    • Homework

• Wednesday: 29th July 2020: Advanced Machine Learning

  • Leader: Adam
  • 9:30-11:00
    • Generalisation
      • Bias-Variance Dilema
    • Kernel methods
      • SVM
      • kernels
  • 11:00-11:30
    • Coffee
  • 11:30-1:00
    • Ensemble Techniques
    • Bagging, random forest and Boosting
  • 1:00-2:00
    • Lunch
  • 2:00-3:30
    • Bayesian Inference
  • 3:30-4:00
    • Coffee
  • 4:00-5:00
    • Probability Models
      • Gaussian Processes and Naive Bayes
    • Homework

• Monday 3rd August 2020: Deep Learning

  • *Leader: Jonathon
  • 9:30-11:00
    • Why Deep
      • CNNs
      • RNNs (LSTM, etc.)
  • 11:30-12:00
    • Coffee
  • 12:00-1:00
    • Word Embeddings
    • Loss functions
    • GPU programming (libraries)
  • 1:00-2:00
    • Lunch
  • 2:00-3:30
    • Keras tutorial 1 - building simple CNNs
    • Transfer Learning
    • Keras tutorial 2 - transfer learning with CNNs
  • 3:30-4:00
    • Coffee
  • 4:00-5:00
    • Keras tutorial 3 - Text classification
    • Keras tutorial 4 - Sequence modelling
    • Current research challenges
      • Visual
        • segmentation
        • object detection
        • multi-label classification
      • Text
        • sequence-sequence learning
          • translation, embedding, etc
          • logical inference & QA
      • Cross-modal transfer
        • generating from embeddings
        • VQA
      • GANs
    • Homework

• Tuesday 4th August 2020: Practical Machine Learning

  • Leaders: Prof Niranjan, Prof Prugel-Bennett and Dr Hare
    • Workshop on data you provide
    • We will look at (slides):
      • Analyse the problem
      • Visualise the data
      • Cleaning the data
      • Using machine learning libraries
      • Evaluate performance
    • 11:30-12:00 Coffee
    • 1:00-2:00 Lunch
    • 3:30-4:00 Coffee