Syllabus

Numerical Linear Algebra

Instructor: Dr. Marin Sombra Gómez & Dr. Arturo Vieiro
Credits: 6 ECTS
Schedule: Wed 3pm-5pm / Fri 5pm-7pm
Semester: Fall
Course Outline:
  1. Standard Problems of Numerical Linear Algebra. General Techniques. Vector and Matrix Norms.
  2. Perturbation Theory. Gaussian Elimination.
  3. Error Analysis in Gaussian Elimination.
  4. Special Linear Systems.
  5. Linear Least Squares Problems. Normal Equations. QR Decomposition.
  6. Orthogonal Matrices. Householder Transformations. Givens rotations. Singular Value Decomposition.
  7. Principal Components Analysis.
  8. Google's PageRank algorithm.
  9. Algorithms for the Nonsymmetric Eigenproblem. Power Method.
  10. Canonical Forms. Computing Eigenvectors from the Schur Form. Inverse Iteration. Orthogonal Iteration.
  11. 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.
  12. Algorithms for the Singular Value Decomposition. Tridiagonal and Bidiagonal Reduction. QR Iteration and Its Variations for the Bidiagonal SVD.

Optimization

Instructor: Dr. Gerard Gómez & Dr. Lluís Garrido
Credits: 6 ECTS
Schedule: Mon 3pm-5pm / Tue 5pm-7pm
Semester: Fall
Course Outline:
  1. Optimization. First examples and background
  2. Unconstrained and constrained optimization with equalities. Optimality conditions
  3. Gradient methods for unconstrained optimization
  4. Alternating directions methods
  5. Constrained optimization
  6. Convexity
  7. Duality
  8. Subgradient methods
  9. Stochastic methods: Genetic algorithms
  10. Stochastic optimization methods
  11. Penalty methods for constrained optimization

Bayesian Statistics and Probabilistic Programming

Instructor: Dr. Josep Fortiana
Credits: 6 ECTS
Schedule: Mon 3pm-5pm / Tue 3pm-5pm
Semester: Spring
Course Outline:
  1. Probability
  2. Random variables
  3. Simulation
  4. The Bayesian paradigm
  5. Markov chains
  6. Bayesian binomial model
  7. More conjugate models
  8. Monte-Carlo methods
  9. Prior distributions
  10. MCMC with a continuous state space
  11. Gibbs sampling
  12. Programming Bayesian simulations
  13. MCMC convergence diagnostics.
  14. Hamiltonian Monte Carlo
  15. Bayesian linear and generalized linear models.

Machine Learning

Instructor: Dr. Oriol Pujol
Credits: 6 ECTS
Schedule: Tue 3pm-5pm / Thu 5pm-7pm
Semester: Fall
Course Outline:
  1. Introduction to Machine Learning
  2. About Data
  3. Performance measures
  4. Dissecting machine learning algorithms
  5. Feasibility of the learning process
  6. Introduction to overfitting
  7. Stochastic Subgradient Methods
  8. Regularization
  9. Uniform bounds
  10. Introduction Probabilistic Models
  11. Gaussian discrimination and PCA
  12. Gaussian processes
  13. Mixture Models
  14. Linear models
  15. Kernels
  16. Ensemble Learning
  17. Neural Networks
  18. Manifold learning

Agile Data Science

Instructor: Dr. Eloi Puertas
Credits: 6 ECTS
Schedule: Thu 3pm-5pm / Fri 3pm-5pm
Semester: Fall
Course Outline:
  1. Introduction to Data Science
  2. Software Engineering & Agile
  3. Scrum
  4. User Stories
  5. Estimating & Planning
  6. Kanban
  7. GIT
  8. PANDAS
  9. Regular Expressions
  10. Web-Scraping
  11. NoSQL
  12. Data Analysis
  13. Data Visualization
  14. Software as a service
  15. Containers

Presentation and Data Visualization

Instructor: Dr. Mireia Ribera
Credits: 3 ECTS
Schedule: Mon 5pm-7pm
Semester: Fall
Course Outline:
  1. Perception and Patterns
  2. Theory. Data and visualization models
  3. Creation of visualizations

Big data *

Instructor: Dr. Jordi Nin
Credits: 3 ECTS
Schedule: Tue 7pm-9pm
Semester: Spring
Course Outline:
  1. Introduction to big data frameworks
  2. Hadoop Framework
  3. HDFS
  4. MapReduce execution model
  5. RDBMS over HDFS: Hive
  6. Spark execution Model
  7. Resilient Distributed Datasets (RDDs)
  8. Supervised Machine Learning with Spark
  9. Unsupervised Machine Learning with Spark

Advanced database techniques *

Instructor: Enric Biosca
Credits: 3 ECTS
Schedule: Mon 7pm-9pm
Semester: Spring
Course Outline:
  1. Big data & Storage
  2. Datawarehouse & Analytcal Information Systems
  3. NoSQL

Deep learning *

Instructor: Dr. Jordi Vitrià
Credits: 3 ECTS
Schedule: Wed 5pm-7pm
Semester: Fall
Course Outline:
  1. Introduction to Deep Learning and its applications. Using the Jupyter notebook & Docker. Software stack.
  2. Basic concepts: learning from data.
  3. Automated differentiation & Backpropagation, Training a Neural Network from Scratch.
  4. Tensorflow programming model. Dense Neural Networks.
  5. Tensorflow ecosystem: Keras, tf-contribution.
  6. Recurrent Neural Netwoks I.
  7. Recurrent Neural Netwoks II.
  8. Embeddings.
  9. Convolutional Neural Networks I.
  10. Convolutional Neural Networks for Large Scale Learning.
  11. Unsupervised Learning I.
  12. Unsupervised Learning II.
  13. Deep Learning & Recommenders.

Recommenders *

Instructor: Dr. Santi Seguí
Credits: 3 ECTS
Schedule: Thu 3pm-5pm
Semester: Spring
Course Outline:
  1. Introduction to Recommender Systems
  2. Non-Personalized Recommenders
  3. Collaborative-Based Recommenders
  4. Dimensionality Reduction for Recommender Systems
  5. Content-Based Recommender Systems
  6. Item-Based Recommender Systems
  7. Evaluation of Recommender Systems
  8. Item-Item methods
  9. Graph Based Recommendations
  10. Deep Learning and Recommender Systems
  11. Context Aware Recommender Systems
  12. Current Practices in Industry and Research

Probabilistic graphical models *

Instructor: -
Credits: 3 ECTS
Schedule: Wed 5pm-7pm
Semester: Spring
Course Outline:
  1. Introduction tp PGM
  2. Markov networks.
  3. Bayesian networks.
  4. Template models
  5. Exact inference. (Variable elimination)
  6. Approximate inference. (Belief propagation / Sampling)
  7. Stan.
  8. Variational inference.
  9. Learning in PGM.
  10. PGM and Deep learning.
  11. Edward, Pyro

Business Analytics *

Instructor: Mariano Yagüez
Credits: 3 ECTS
Schedule: Thu 6pm-8pm
Semester: Spring
Course Outline:
  1. What is Business Analytics?
  2. Impact of Business Analytics in a Company. General approach.
  3. Value Chain in a company.
  4. Canvas model as an alternative.
  5. New Value Chain: Impact of Business Analytics.
  6. Business Analytics impact in Marketing.
  7. Business Analytics impact in Human Resource Management and Organization Models.
  8. How to evaluate new opportunities.
  9. Impact of Business Analytics in different sectors: New Business and transformation.
  10. Framework for the adoption of Business Analytics.

Natural Language Processing *

Instructor: Dr. David Buchaca
Credits: 3 ECTS
Schedule: Tue 5pm-7pm
Semester: Spring
Course Outline:
  1. Introduction to linguistics
  2. NLP Applications
  3. Tokenization and Standarization
  4. Introduction to NLTK
  5. Morphological analysis and Pos-Tagging
  6. Syntax
  7. Parsing
  8. Semantics and NLP
  9. Distributional Semantics
  10. Word embedding

Computer Vision *

Instructor: Dr. Sergio Escalera
Credits: 3 ECTS
Schedule: Wed 3pm-5pm
Semester: Spring
Course Outline:
  1. Image processing principles
  2. Features from images
  3. Image retrieval
  4. Recognizing objects in images
  5. Convolutional Neural Networks
  6. Medical imaging
  7. Image segmentation
  8. Scene understanding and captioning
  9. Face analysis and affective computing

Complex Networks *

Instructor: Dr. Albert Diaz
Credits: 3 ECTS
Schedule: Fri 3pm-5pm
Semester: Spring
Course Outline:
  1. Big networks. Big data
  2. Network data. Representations
  3. Network characterization. Microscale
  4. Network characterization. Macroscale
  5. Network models: random graphs, small worlds, scale-free networks
  6. Network characterization. Mesoscale
  7. Network visualization
  8. Time dependent networks
  9. Dynamics on networks

(* Eligible Course)

In order to successfully finish the master’s degree programme, students are required to complete, during the second semester, a capstone project. Capstone projects are “experiential” projects whereby students take what they have learned during the master’s degree programme and apply it to examine a specific idea.