Intended learning outcomes (knowledge, skills and competences to be developed by the students)

This curricular unit has four main objectives: 

• Introduce basic analytical and quantitative methods
• Introduce python programming
• Introduce machine learning models
• Provide students with sufficient knowledge to motivate independent exploration of introduced material

Syllabus

• Brief introduction to Linear Algebra: vectors and matrices, addition and scalar multiplication, matrix multiplication, matrix inversion and transpose
• Brief introduction to Calculus: basic differentiation and the chain-rule
• Brief introduction to Statistics: probability, law of total probability, Naïve Bayes, random variable, gaussian distribution, confidence intervals
• Introduction to Python programming, including widely-used packages such as NumPy, Matplotlib, SciPy and Scikit-Learn
• Introduction to ML:
  • a. Supervised learning: regression and classification, basic concepts such as feature vectors and outcomes
  • b. Linear regression: cost function and gradient descent
  • c. Optimization: global and local minima, choice of learning step
  • d. Evaluation and generalization: evaluation of classifiers and regressors, loss function, generalization and overfitting, training set, validation set and test set
  • e. Neural networks: McCulloch & Pitts model, perceptron, multi-layer perceptron, different activation functions, backpropagation algorithm, introduction to convolutional neural networks