Cristiane da Anunciação Souza

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
LG3: 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

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

Exam: 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.

Isabel Machado Alexandre

Ana Maria de Almeida

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 is as follows:
PC1: Object-based representation
PC2: Structured Descriptions
PC3: Ontologies and Knowledge Domain Representation
PC4: Knowledge Representation in a Social Context (Semantic Web)
PC5: Logic Programming
PC6: Non-monotonic Logic and ASP-Answer Set Programming
PC7: Uncertainty and Degrees of Belief
PC8: Abductive Reasoning
PC9: Qualitative Reasoning
PC10: Constraint Satisfaction
PC11: Representation and Reasoning by Actions and Plans
PC12: Abstraction, Reformulation and Approximation

In the assessment throughout the semester, students will have to take:
- Individual written test on the entire course syllabus (60%) - to be taken in the exam season (1st or 2nd exam).
- Research work (in groups) on one of the UC topics, with a report and oral presentation (40%). The oral presentation is made in class time during the semester. The grade for the research paper is divided 50% between each component and group members can have different grades.
Both assessment components in the semester-long assessment have a minimum mark of 8.

Alternatively, students can take only one exam (100%), which can be on both exam dates.
In the special exam period, students take the exam (100%).

Ricardo Ribeiro

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.

Approval for this course can only be obtained through assessment throughout the semester; the exam modality is not considered.

Assessment elements:
- 4 practical exercises (10% each), including code and a report, in groups of 2 members during the academic period with an in-person discussion;
- 4 mini-tests (5% each) during the academic period;
- A project (40%) in groups of 2 members that includes a report (limited to 10 pages), code, and an oral presentation (approximately 10 minutes), to be conducted during any of the assessment periods — the project must be submitted up to one week before the chosen assessment period.

The special assessment period will consist of the project, done individually, to be submitted one week before the special period, and a written test that replaces the practical exercises and mini-tests. The weights of these assessment elements are the same as previously indicated.

Attendance is not used as a criterion for evaluation or failure.

Cristiana João da Silva

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.

PC1-Introduction and review
1.1- Introduction
1.2 - Linear and quadratic programming
1.3 - Differential Calculus, Unrestricted and Restricted Optimization.
1.4 - Numerical methods

PC2 - Metaheurísticas
2.1- Simulated Annealing
2.2 - Tabu Search
2.3 - Evolutionary Algorithms

PC3 - 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:
- Assessment throughout the semester: 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.
The minimum passing grade for this course is 9.50 points (out of 20), rounded to a final grade of 10 points.

Jorge Miguel da Rocha

LO1. Know fundamental concepts of linear algebra, probability and information theory.
LO2. Apply the previous techniques (LO1) in the context of machine learning, using, in particular, Kernel methods and Gaussian processes in regression and classification problems.
LO3. Master basic Fourier and wavelet analysis techniques.
LO4. Employ the previous methods (LO1 and LO3) in the context of signal and image processing.
LO5. Apply basic dynamic programming algorithms to solve problems using reinforcement learning.
LO6. 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.
4. Principal components analysis.

II - Signal processing.
1. FFT and convolution.
2. Discrete Wavelets.
3. Applications to sound and image processing.

III - Dynamic programming and reinforcement learning.
1. The context of reinforcement learning.
2. Bellman’s equation.
3. Iterative methods and applications.
4. Monte Carlo methods.

The evaluation will be based on 4 problem sets (25% each), performed individually. Each set will have a written component and a Python implementation component. Students might be asked to present some of their work orally.
The special season is reserved for the cases identified in Article 14 of the "Regulamento Geral de Avaliação de Conhecimentos e Competências" (RGACC) and it will consist of a single problem set (100%), to be undertaken individually, and covering all of the syllabus of the course.

João Costa

LO1: Recognize the various components of a deep learning model with neural networks.
LO2: Implement stand-alone programs, using python, of simplified versions of the components implicit in LG1.
LO3. Relate different architectures to solve different problems.
LO4. Apply regularization techniques to improve the performance of deep learning models.
LO5. Know in detail and apply the DQN algorithm in the context of reinforcement learning.
LO6. Use the Keras library to implement deep learning models to solve problems in image recognition, natural language processing and reinforcement learning.
LO7. Know fundamental theorems about asymptotic neural networks and apply these results in the critical analysis of DL models

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

Approval with a grade not lower than 10 out of 20 in one of the following modalities:
- Assessment throughout the semester v1: exercise worksheets (70% in total) completed individually + group project (30%).
- Assessment throughout the semester v2: exam (70%), taken during one of the exam periods + group project (30%).
- Assessment by exam: exam (100%), taken during one of the exam periods.
> Each exercise worksheet will have a written component and a Python implementation component. The solutions presented are subject to discussion.
> Group projects must be completed in groups of up to 4 members and are subject to discussion. They consist on developing a deep learning application.

Ana Maria de Almeida

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

This course is mainly concerned with cutting-edge concepts and methods in a state of the art that is still evolving, it does not require a 100 per cent written exam.
Students are assessed using the group work in the workshops (GW), by reading a conference/journal article and presenting it to the peers at the end of the semester (RP), and writing an individual research paper (IR) to be delivered ar at specific date during the 1st examination period. The grade is calculated by: 0,3 x GW + 0,3 x RP + 0,4 x IR.

Students are assessed through:
(a) group work in workshops (GW),
(b) presenting a conference or journal paper (RP) to peers (at the end of the semester)
(c) an individual research paper (IR) (on a set date in the 1st term),
according to the formula: 0.3 x GW + 0.3 x RP + 0.4 x RI.
For approval, any assessment element requires a minimum mark of 8.

Luís Nunes

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

Assessment throughout the semester: Presentation of a group project (groups of no more than two people, at the end of the term, 50%) and submission of an individual article on the experience (1st or 2nd term, 50%). If the student is entitled to EEF, they can submit both components of the assessment or just one of them if the other has already been positively assessed in the same academic year. Minimum mark of 8 in both assessments. 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.