Course Syllabi

Mandatory Courses Contents
Numerical Linear Algebra
  • Standard Problems of Numerical Linear Algebra. General Techniques. Vector and Matrix Norms.
  • Perturbation Theory. Gaussian Elimination.
  • Error Analysis in Gaussian Elimination.
  • Special Linear Systems.
  • Linear Least Squares Problems. Normal Equations. QR Decomposition.
  • Orthogonal Matrices. Householder Transformations. Givens rotations. Singular Value Decomposition.
  • Principal Components Analysis.
  • Google’s PageRank algorithm.
  • Algorithms for the Nonsymmetric Eigenproblem. Power Method.
  • Canonical Forms. Computing Eigenvectors from the Schur Form. Inverse Iteration. Orthogonal Iteration.
  • Iterative Methods for Linear Systems. Basic Iterative Methods. Jacobi’s Method. Gauss Seidel Method. Successive Overrelaxation. Convergence of Jacobi’s, Gauss-Seidel, and SOR(w) methods on the Model Problem. Detailed Convergence Criteria for Jacobi’s, Gauss Seidel, and SOR(w) Methods.
  • Algorithms for the Singular Value Decomposition. Tridiagonal and Bidiagonal Reduction. QR Iteration and Its Variations for the Bidiagonal SVD.
  • Optimization. First examples and background
  • Unconstrained and constrained optimization with equalities. Optimality conditions
  • Gradient methods for unconstrained optimization
  • Alternating directions methods
  • Constrained optimization
  • Convexity
  • Duality
  • Subgradient methods
  • Stochastic methods: Genetic algorithms
  • Stochastic optimization methods
  • Penalty methods for constrained optimization
Bayesian Statistics and Probabilistic Programming.
  • Probability
  • Random variables
  • Simulation
  • The Bayesian paradigm
  • Markov chains
  • Bayesian binomial model
  • More conjugate models
  • Monte-Carlo methods
  • Prior distributions
  • MCMC with a continuous state space
  • Gibbs sampling
  • Programming Bayesian simulations
  • MCMC convergence diagnostics.
  • Hamiltonian Monte Carlo
  • Bayesian linear and generalized linear models.
Machine Learning
  • Introduction to Machine Learning
  • About Data
  • Performance measures
  • Dissecting machine learning algorithms
  • Feasibility of the learning process
  • Introduction to overfitting
  • Stochastic Subgradient Methods
  • Regularization
  • Uniform bounds
  • Introduction Probabilistic Models
  • Gaussian discrimination and PCA
  • Gaussian processes
  • Mixture Models
  • Linear models
  • Kernels
  • Ensemble Learning
  • Neural Networks
  • Manifold learning
Agile Data Science
  • Introduction to Data Science
  • Software Engineering & Agile
  • Scrum
  • User Stories
  • Estimating & Planning
  • Kanban
  • GIT
  • Regular Expressions
  • Web-Scraping
  • NoSQL
  • Data Analysis
  • Data Visualization
  • Software as a service
  • Containers
Presentation and Data Visualization
  • Perception and Patterns
  • Theory. Data and visualization models
  • Creation of visualizations
Ethical Data Science
  • Data science has the potential to be both beneficial and detrimental to individuals and/or the wider public. To help minimise any adverse effects, data scientists can seek to understand the potential impact of their work and consider any opportunities that may deliver benefits for the public. This course, focused on ethics specifically related to data science, will provide the student with the framework to analyze these concerns. This framework will include theoretical basis as well practical approaches to avoid or mitigate potential problems.
Final Master Project
Optional Courses Contents
Big Data
  • Introduction to Big Data.
  • Introduction to classical computing
  • Evolution of Big Data
  • Introduction to Cloud Infrastructure
  • Introduction to Docker and Kubernetics
  • Big Data Storage.
  • Technologies of NoSQL Database and management systems
  • Introduction to messaging systems
  • Kaffka and Stream processing
  • HDFS/S3
  • Introduction of distributed storage
  • Advanced HDFS
  • Introduction to S3 and basic data access
  • Big Data Ingestion
  • ETL Management
  • Introduction to Distributed processing.
  • Introduction to Spark
  • Data Science Life cycle Managment
Deep Learning
  • Introduction to Deep Learning and its applications.
  • Automated differentiation & Backpropagation, Training a Neural Network from Scratch.
  • Tensorflow programming model. Dense Neural Networks.
  • Tensorflow ecosystem: Keras, tf-contribution.
  • Recurrent Neural Netwoks.
  • Embeddings.
  • Convolutional Neural Networks.
  • Convolutional Neural Networks for Large Scale Learning.
  • Unsupervised Learning I.
  • Unsupervised Learning II.
  • Deep Reinforcement Learning.
  • Introduction to Recommender Systems
  • Non-Personalized Recommenders
  • Collaborative-Based Recommenders
  • Dimensionality Reduction for Recommender Systems
  • Content-Based Recommender Systems
  • Item-Based Recommender Systems
  • Evaluation of Recommender Systems
  • Item-Item methods
  • Graph Based Recommendations
  • Deep Learning and Recommender Systems
  • Context Aware Recommender Systems
  • Current Practices in Industry and Research
Probabilistic Graphical Models
  • Introduction tp PGM
  • Markov networks.
  • Bayesian networks.
  • Template models
  • Exact inference. (Variable elimination)
  • Approximate inference. (Belief propagation / Sampling)
  • Stan.
  • Variational inference.
  • Learning in PGM.
  • PGM and Deep learning.
  • Edward, Pyro
Business Analytics
  • What is Business Analytics?
  • Impact of Business Analytics in a Company. General approach.
  • Value Chain in a company.
  • Canvas model as an alternative.
  • New Value Chain: Impact of Business Analytics.
  • Business Analytics impact in Marketing.
  • Business Analytics impact in Human Resource Management and Organization Models.
  • How to evaluate new opportunities.
  • Impact of Business Analytics in different sectors: New Business and transformation.
  • Framework for the adoption of Business Analytics.
Natural Language Processing
  • Introduction to linguistics
  • NLP Applications
  • Tokenization and Standarization
  • Introduction to NLTK
  • Morphological analysis and Pos-Tagging
  • Syntax
  • Parsing
  • Semantics and NLP
  • Distributional Semantics
  • Word embedding
Computer Vision
  • Image processing principles
  • Features from images
  • Image retrieval
  • Recognizing objects in images
  • Convolutional Neural Networks
  • Medical imaging
  • Image segmentation
  • Scene understanding and captioning
  • Face analysis and affective computing
Complex Networks
  • Big networks. Big data
  • Network data. Representations
  • Network characterization. Microscale
  • Network characterization. Macroscale
  • Network models: random graphs, small worlds, scale-free networks
  • Network characterization. Mesoscale
  • Network visualization
  • Time dependent networks
  • Dynamics on networks
Data Science for Health
  • Big data arising in the biomedical sciences and public health, including but not restricted to various forms of “omics” data, imaging data, geospatial data, mobile health data and electronic health records, present unprecedented challenges and opportunities for research and development. This course will focus on specific methods for data collection and preparation, data analytics methods and tools as well as how to generate and communicate meaningful insight from analytics.