By the end of this course, the student should be able to:
LG1: Know the origins of the emotion-cognition debate
LG2: Know the main theoretical perspectives on the relationship between emotion and cognition
OA3: Know, analyse and evaluate the main methods and research techniques on the influence of emotions on cognition, and on the cognitive factors involved on emotions.
LG4: Know and explain the influence of emotions on cognitive and socio-cognitive processes
LG5: Understand the practical implications of this field, being able to apply the acquired knowledge to a range of contexts

1. Definitions and assumptions regarding the cognition-emotion debate
1.1. Cognition: notions of cognitive representation and of information processing; overview of cognitive functions
1.2. Emotion and related concepts
1.3. Historical and philosophical aspects of the cognition-emotion debate
1.4. Methodological approaches to the study of cognition-emotion interactions
2. The influence of emotion on cognition
2.1. Judgment, decision-making and processing modes
2.2. Attention and cognitive control
2.3. Memory
2.4. Language
2.5. Emotional traits and cognitive performance
2.6. Affective disorders
3. The influence of cognition on emotion
3.1. Cognitive processes and emotion regulation
3.2. Impact of cognitive disorders on emotion
4. Integration of cognitive and emotional processes: interactions in the brain

Periodic: Group assignment, including the discussion of a paper (10%) and a written report on the topic (20%); individual response to 2 questions (20%); written test (50%). Students will get approval if they achieve at least 9.5 points in each of the evaluation elements.

Final: Students will get a final test (1st and/or 2nd season), according to the REACC. Students will get approval if obtaining at least 9.5 points in that evaluation moment.

The learning outcomes follow establisehd international standards and are the following:
LO1. Know several of the existing knowledge and reasoning systems.
LO2. Understand how to represent knowledge and to reason for each system.
LO3. To grasp the advantages and shortcomes of each system.
LO4. Be able to choose the proper system when confronted with a given problem.
LO5. Know how to build knowledge bases for each system.
LO6. Be able to represent and solve real problems involving knowledge representation and reasoning by using diverse systems.

The syllabus contents (SC) are:
SC1: Object-oriented representation
SC2: Structured Descriptions
SC3: Ontologies and representation of Domain Knowledge
SC4: Knowledge Representation in Social Context (Semantic Web)
SC5: Logic Programs
SC6: Nonmonotonic logic and answer sets: ASP-Answer Set Programming
SC7: Vagueness and Degrees of Belief
SC7: Abductive Reasoning
SC8: Qualitative Reasoning
SC9: Constraint Satisfaction
SC10: Representation and Reasoning with actions and plans
SC11: Abstraction, Reformulation and Approximation

Students are assessed using the group work in the workshops (GW), by reading conference and journal articles and presenting an
individual research paper (IR), and write an individual report of the seminar classes (RS). The grade is claculated by: 0,3 x GW + 0,3 x RS + 0,4 x IR

At the end of the course the student should be able to:
OA1. Identify the main historical milestones of ML.
OA2. Know its relations with other scientific areas.
OA3. Enumerate and recognize some of its applications.
OA4. Know the characteristics of the main algorithms in the field of Machine Learning.
OA5. Know, and be able to explain, the main concepts of an algorithm that exemplifies: Supervised Learning (symbolic and sub-symbolic), Unsupervised Learning, Reinforcement Learning and Search Algorithms.
OA6. Explain in full detail one of the learning algorithms studied.
OA7. Implement a learning algorithm or use one in a non-trivial problem.

CP1. Historical notes on Machine Learning. Relationship with other displines. Applications.
CP2. Machine Learning problems and approaches;
CP3. Unsupervised Learning;
CP4. Supervised Learning (symbolic and sub-symbolic);
CP5. Reinforcement Learning;
CP6. Search methods and Genetic/Evolutionary Algorithms;
CP7. Data pre-processing, results validation;
CP8. Speedup of ML algorithms.
CP9. ML algorithm implementation

It is only possible to pass this course by periodic assessment. It does not include assessment by exam.

Assessment elements:
- 4 practical exercises including a mini-test (15% each), during the teaching period;
- project in groups of 2 (40%) which includes a report (with a limit of 10 pages), code and oral presentation (approximately 10 minutes), to be carried out in any of the assessment periods - the project must be handed in no later than one week before the chosen assessment period.

The special assessment period will consist of the project and a written test which replaces the practical exercises.

Attendance is not used as an evaluation or failure criterion.

At the end of the course, the student should be able to:
LG1 - Use linear and quadratic optimization methods.
LG2 - Apply numerical methods of classical optimization.
LG3 - Understand, apply and adapt some metaheuristics.
LG4 - Understand, apply and adapt the most important gradient descent methods.

1-Introduction and review
1.1- Introduction
1.2- Linear and quadratic programming
1.3 – Differential Calculus, Unrestricted and Restricted Optimization.
1.4 – Numerical methods
2- Metaheurísticas
2.1- Simulated Annealing
2.2- Tabu Search
2.3- Evolutionary Algorithms
3-Gradient descent and variations
3.1 Gradient Descent
3.2 Stochastic Gradient Descent
3.3 Momentum
3.4 Adagrad
3.5 Others

The modes of assessment are:
- Periodic assessment: test (50%) + assignments (50%), or- Assessment by Examination (100%).
- Approval in periodic assessment requires a minimum score of 9.0 out of 20 on the test.

LG1. Know fundamental concepts of linear algebra, probability and information theory.
LG2. Apply the previous techniques (LG1) in the context of machine learning, using, in particular, Kernel methods and Gaussian processes in regression and classification problems.
LG3. Master basic Fourier and Wavelet analysis techniques.
LG4. Employ the previous methods (LG1 and LG3) in the context of signal, image and speech processing.
LG5.Apply basic dynamic programming algorithms to solve problems using reinforcement learning.
LG6. Implement the aforementioned techniques in python.

I - Linear algebra, probabilities and information 1. Inner products and matrix decomposition.
2. Random variables, information and entropy
3. Kernel methods and Gaussian processes in regression and classification.
II - Signal processing
1. Principal components analysis.
2. FFT and convolution.
3. Compressed sensing.
4. Discrete Wavelets.
5. Applications to sound, image and speech processing.
III - Dynamic programming and reinforcement learning.
1. (Invited lecture) Behavioral psychology and learning.
2. The context of reinforcement learning.
3. Bellman’s equation.
4. Iterative methods and applications.
5. Monte Carlo methods.

Classes will be conducted according to the following learning methodologies (LM):
LM1.Exposition and discussion
LM2. Problem solving
LM3. Self-study, in accordance with the weekly class planning
LM4. Invited lectures
Concerning LM4, we expect to carry out one invited lecture to be presented by a professor of the Department of Social and Organizational
Psychology (conditional on availability)

LG1: Recognize the various components of a deep learning model with neural networks.
LG2: Implement stand-alone programs, using python, of simplified versions of the components implicit in LG1.
LG3. Relate different architectures to solve different problems.
LG4. Apply regularization techniques to improve the performance of deep learning models.
LG5. Know in detail and apply the DQN algorithm in the context of reinforcement learning.
LG6. Use the Keras library to implement deep learning models to solve problems in image recognition, natural language processing and reinforcement learning.
LG7. Know fundamental theorems about asymptotic neural networks and apply these results in the critical analysis of DL models

1. (Invited lecture) Neurosciences and artificial neural networks.
2. Mathematical models of neurons and activation functions.
3. Efficient algorithms for matrix manipulation and tensor algebra.
4. Backpropagation and automatic differentiation.
5. Classification and regression problems with feedforward neural nets.
6. (Invited lecture) Hardware: AI accelerators for machine learning.
7. Universal aproximation theorems and asymptotic analysis.
8. Convolution networks and image recognition.
9. Regularization techniques.
10. Deep reinforcement learning.
11. (Invited lecture) Applications of deep learning in science and industry.

Evaluation will be based on 4 problem sets (25% each), performed individually. Each set will have a small written component and a principal component related to python implementation. Students might be asked to defend some of their work orally.

LO1 Apply relevant standards, ethical, social, privacy, and governance considerations, and thus demonstrate an understanding of issues related to the practice of an AI professional.
LO2 Analyse and discuss social impact and professional issues related to AI and deployment of AI systems, evaluating the implications of delegating control and decision making to in intelligent systems, including issues on fairness, bias, transparency, accountability and explainability of AI.
LO3 Analyse and evaluate case studies, and to assess the work of peers.
LO4 Communicate effectively to a variety of audiences through a range of modes and media, specifically, through written technical reports and visual and oral presentations.
LO5 Apply responsible and ethical research principles and choose appropriate methods to analyse, theorise and justify conclusions in AI professional practice and research.

S1 Introduction: a brief history of AI
S2 How AI works
S3 Bias, Ethics, Fairness, and Privacy, Robustness; Thrustworthiness;
S4 Regulatory frameworks
S5 AI for the present: case studies
S6 The interpretability challenge: XAI
S7 AI for the future: special topics in AI

Students are assessed using the group work in thw workshops (GW), by reading conference and journal articles and presenting these
(RP), and write an individual research paper (IR), and the grade is claculated by: 0,3 x GW + 0,3 x RP + 0,4 x IR

The student, upon completion of the UC, should:
OA1: Know a process for organizing AI projects
OA2: Know how to write a scientific paper based on the results of an experiment
OA3: Have gained experience of the tasks usually involved in an AI project OA4: Have contact with the problems inherent to the use of realistic data

P1. CRISP-DM
P2. Introduction to scientific paper writing
P3. Introduction to project organization and management
P4. IA project practice

Periodic Assessment: Presentation of a group project (groups of two people maximum, end of term, 50%) and submission of an individual paper on the experience (1st or 2nd term, 50%). If the student is entitled to EEF, he may deliver both components of the assessment, or only one of them if the other has already been positively assessed in the same academic year. This subject does not have a final exam

OA1: Understand the main neural network architectures for processing sequential data
OA2: Apply simplified versions of some of the sequential data processing architectures to concrete problems
OA3: Describe the operation of generative models, such as Generative Adversarial Networks, Variational Autoencoders and Flow-based models, and autoregressive models
OA4: Describe the architecture of transformer-based and self-attention models, such as BERT, GPT-2 and GPT-3, as well as variants of these models
OA5: Apply pre-trained transformer-based models to case studies, making use of transfer learning OA6: Know current trends in applying language models to real problems

Introduction, Revisiting Neural Networks (Feed Forward networks, Backpropagation) P1: Sequential data
- Recurrent Neural Networks
- Learning challenges and solutions
- Conditional sequence models
- LSTMs
- CNNs for sequential data
- Learning with attention- ELMO as a case study
P2: Generative Modeling
- GANs
- Variational autoencoders (VAE)
- Flow-based models
- Autoregressive models
P3: Transformers & self-attention
- BERT, GPT2 and GPT-3, and BART
- Transfer learningP4: Recent Trends:
- LaMDA: Language Models for Dialog Applications
- Responsibility first

Periodic evaluation: Intermediate Test (25%) + PROJECT (35%) + Final Test (40%). Students take the final exam if they have opted for that type of evaluation, or have not obtained a positive grade in the periodic evaluation. The final exam consists of an individual test that covers the whole syllabus of the course. Attendance is not an essential requirement for passing.