Objectives of Programme's Learning Outcomes

• Master expertise.
• Have developed the knowledge and skills acquired in the previous cycle to a level that extends beyond the Bachelor's course in Physics, and which provides the basis for the development and implementation of original ideas in a professional context.
• Grow personally and professionally.
• Have developed the skills that will enable them to continue to acquire knowledge independently.
• Have a creative and rigorous scientific approach
• Gather and interpret relevant scientific data and critically analyse it, distinguising working hypotheses of proven facts.

Learning Outcomes of UE

develop an applied pattern recognition system, together with a critical analysis of the problem;
apply image analysis and segmentation techniques
apply data processing techniques (feature extraction, feature selection);
apply classification and machine learning techniques (Gaussian models, Clustering, Artificial Neural Networks, Dynamic Time Warping, Hidden Markov Models, Deep Neural Networks);
estimate performances of classifiers.

Content of UE

Image Processing: Image acquisition; lowlevel processing, filtering, transforms; image segmentation and registration;
Pattern Recognition: SPR scheme, feature extraction, classifiers, combining classifiers; neural networks:feed-forward neural networks, training MLP, Deep Neural Nets; support vector machines; dynamic systems: dynamic time warping, hidden Markov models

Prior Experience

fundamentals of signal processing; probability and statistics

Type of Assessment for UE in Q1

• Oral examination

Q1 UE Assessment Comments

Evaluation methods may be adjusted according to the teaching/evaluation context imposed by health measures.

Type of Assessment for UE in Q3

• Oral examination

Q3 UE Assessment Comments

Evaluation methods may be adjusted according to the teaching/evaluation context imposed by health measures.

Type of Resit Assessment for UE in Q1 (BAB1)

• N/A

Q1 UE Resit Assessment Comments (BAB1)

Not applicable