readme.md

Foundations of Machine Learning in Pythons

Three weeks 15 days, with a lecture and an exercise every day.

Prerequisites:

• Basic programming in Python If you are not yet familiar with python, please consult: https://docs.python.org/3/tutorial/ before the first session.

Course contents

• Introduction: What is machine learning, and what can it do for us?

• Linear Algebra (Elena)

  • Matrix multiplication

  • Eigenvalues and principal component analysis (PCA).

  • Linear dimensionality reduction using PCA.

  • Reading: https://www.deeplearningbook.org/contents/linear_algebra.html

• Statistics - Probability Theory(Elena)

  • random variable

  • mean and variance

  • common probability distributions

  • correlation and auto-correlation

  • Reading: https://www.deeplearningbook.org/contents/prob.html

• Calculus (Moritz)

  • Gradients

  • Optimization

  • Gradient descent

  • Reading: https://www.deeplearningbook.org/contents/optimization.html

• Foundations of machine learning (Elena)

  • overfitting and underfitting
  • clustering
  • non-linear dimensionality reduction using t-SNE (seed dependent).
  • Decision trees and random forests
  • Support vector machines
    • SVM classification
    • SVM time series prediction.

• Deep feedforward networks (Moritz)

  • Image Analysis
    • Fully connected networks
      • image classification
      • time series prediction
    • Convolutional neural networks
      • CNN for image classification
      • CNN for image segmentation
  • Optimization for deep neural networks

  Reading: https://www.deeplearningbook.org/contents/mlp.html, https://www.deeplearningbook.org/contents/convnets.html, and https://www.deeplearningbook.org/contents/optimization.html

• Interpretability and Sequence learning (Moritz)

  • Integrated gradients
  • Sequence to sequence models (i.e. machine translation)

Course calendar

1. Installation day:

   • Lecture:

     • setup vscode
     • creating an array
     • plotting an array

   • Exercise:

     • Installation instructions
     • Recap of the python tutorial: https://docs.python.org/3/tutorial/

2. Linear Algebra:

3. Statistics - Probability Theory: Lecture:

   • random variable
   • mean and variance
   • common probability distributions

   Exercise:

   • setting the seed!
   • Generating random variables.

4. SVM exercise: https://archive.ics.uci.edu/ml/datasets/iris