Master Thesis
Evaluation Guidelines
The master thesis project is evaluated by a committee constituted by three members: the thesis supervisor and two other members of the department. This evaluation considers the tutoring sessions, the oral presentation and the written report.
Important dates
| Early Jan | Agree with your supervisor on a topic |
| 31 March | First draft containing motivation, context, state of the art and scientific questions. |
| Late June | Submission of the draft report to the panel committee. |
| July | Oral presentations and submission of the final report to the panel committee. |
Oral presentation
Oral presentations of the thesis will be scheduled in mid July. They will take 20 minutes plus 10 minutes of questions from the evaluation committee.
Thesis report
The student has to submit a draft version of the thesis report to the evaluation committee before June 30th. Accordingly, the student and the supervisor have to arrange that the supervisor has enough time to read and assess the final thesis text before the presentation. The final version of the report must be submitted to the panel committee before the oral presentation.
Formatting of the report
As for the format of the written thesis (Font size, line spacing, margins, Section numbering etc) we propose that the students follow the template provided by the Universitat Pompeu Fabra for master theses. For Latex you can use this one. The MIIS board does not have any preference on the word processor and will accept documents written with any word processor.
The actual report can be structured according to Introduction, State of the Art, Methods, Results, Discussion and Conclusion. However, this is not mandatory. Different overall organizations of the report can be used, if necessary. As a general guideline we would like to indicate that a Master report is not supposed to reach the comprehensiveness of a PhD thesis. An adequate length of the thesis is between 30-50 pages (this number is regarded as a guideline).
More Information
Proposed thesis topics
Title & Description |
Supervisor(s) |
|
Master Thesis Proposals at Eurecat technology centre This year, the Robotics and Automation Unit at Eurecat is offering different proposals to be developed as a Master Thesis, which are listed below. If the student has its own proposal, it also could be taken it in consideration. |
|
|
AI and fitness The European Commission recently approved the creation of the European Health Data Space (EHDS), which will be a sovranational repository of medical data usable for personalized care, research and clinical studies. However, its implementation is complicated by technical, ethical and regulatory difficulties. In this project, we would like to create a use case with wearables like smartwatches to understand real-world implementation challenges. The technical pipeline would explore federate learning of a personal AI assistant that uses data from smarwatch activities to recommend training activities and evaluate that against compliance with the new AI regulation: AI Act, GDPR and the upcoming EHDS requirements. |
|
|
AI as a scientific assistant Given the overwhelming amount of new papers every day, new strategies are needed to find, categorize and understand them. In this project we will refine an existing mutliagents pipeline that searches, downloads and processes scientific papers to generate insights for scientific researchers in the European Commission using LLMs and graph techniques. |
|
|
Reasoning with language and knowledge graphs Large language models (LLMs), are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia and Firebase for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolving by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and simultaneously leverage their advantages. In this project, we will work jointly towards a system that unifies LLM and KGs for the processing of scientific literature and technical reports from the European Commission. |
|
|
Efficient policies for constrained reinforcement learning In this project, we will study decision-making algorithms under requirements. Many practical applications make use of learning algorithms which are required to satisfy constraints such as safety, energy use or robustness. Under the reinforcement learning framework, it is the agent who learns to satisfy these by interacting with the environment, in what is known as constrained reinforcement learning. We will study constrained reinforcement learning formulations and exploit recent developments in duality theory to improve on current solutions, designing efficient and versatile methods capable of guaranteeing near-optimality and minimal constraint violation. |
|
|
Task-uncertain reinforcement learning In this project we will study the problem of designing reinforcement learning policies in settings where we do not know beforehand which task must be performed. We will consider reinforcement learning problems with different objectives (rewards), each describing a task that may need to be performed during deployment (e.g., deviating from a large or small obstacle). At execution time, the agent must decide which task to perform by interacting with the environment and collecting rewards. In other words, in this project, we will design and test algorithms exploiting rewards not only to learn how to perform tasks, but also to identify which task to perform. |
|
|
Heuristic design for dynamic feature selection In some situations, information usage must be minimized, for instance in a medical diagnostic setting, where acquisitions can be invasive or dangerous for the patient. Reinforcement learning allows to optimally solve this problem, proposing at each step the modalities that will minimize the information/cost balance based on the currently acquired data not only greedily, but also accounting for future decisions. However, exploring the search space of all possible features combinations is computationally unfeasible. In this thesis, you will explore heuristics to quickly discard regions of the space that are not relevant due to their low value. In particular, you will derive confidence bounds for sampling-based heuristics that will allow to balance the exploration-exploitation trade-off. |
|
|
Algorithmic hiring This is a project in the algorithmic fairness space, and is part of Horizon Europe project FINDHR. Algorithmic hiring is the usage of tools based on Artificial intelligence (AI) for finding and selecting job candidates. As other applications of AI, it is vulnerable to perpetuate discrimination. There are various subprojects that can be done here, including generation of synthetic data, study of ranking and recommendation algorithms, and external audits of actual hiring platforms. |
|
|
Gender bias in online platforms This project will analyze and study potential gender biases of online platforms. These may include job search engines, e-commerce websites, search engines, and platform economy sites for which some data could be scrapped/obtained. The specific platform is to be decided with the master student. The work will involve data scrapping/collection, measurement through fair ranking/recommendation algorithms, and analysis of potential biases found. It requires solid knowledge of Python and desire to work within a framework of data feminism, which seeks to eliminate gender biases in data collection and data processing pipelines. |
|
|
Risk-Prediction Instruments in Criminal Justice The Justice Department of Catalonia has been using for several years structured risk prediction instruments, similar to COMPAS in the US or OASIS in the UK, to predict the risk of recidivism and violent recidivism. Correctional officers, psychologists, and social workers apply a questionnaire to juvenile offenders and to people who have been convicted for a crime (these are different questionnaires); the questionnaire is then processed using a model trained on thousands of previous cases, and an output is produced, which is then interpreted by the person applying the instrument. Detailed anonymized data is available for studying to what extent different instruments can be biased against different sub-populations (e.g., immigrants or children of immigrant). Additionally, we would like to explore the potential for new risk prediction instruments. The work would be done in collaboration with researchers on criminology at the University of Barcelona and at the Justice Department of Catalonia. |
|
|
Monitoring of Artificial Intelligence incidents and hazards The proposed project aims to develop an analysis on the OECD AI Incident Monitor (AIM) database, which documents incidents and hazards related to artificial intelligence. This monitor is a fundamental tool for public policy makers, AI professionals and other stakeholders at an international level to understand the risks and harms associated with AI systems. In this regard, students interested in developing a project to explore the impacts documented by the AIM, conduct a practical analysis with recommendations and possible future scenarios on risks from the use of AI are invited. |
|
|
Graph Neural Networks for Large-scale Optimization Large-scale constrained optimization problems are frequently encountered in real-world applications, e.g. traffic management, logistic planning, warehouse optimization, multiagent planning, and scheduling, to name a few. Though constrained optimization problems have been extensively studied, because of their computational complexity, existing optimal solvers do not scale well to complex problems. Recently, graph neural networks (GNNs) have been successfully applied to approximate solutions to large optimization problems. The aim of the thesis is to study the potential of graph neural networks for large-scale optimization, and test it in realistic applications. |
|
|
Linearly-solvable Markov decision processes with function approximation A linearly-solvable Markov decision process (LMDP) is a special case of the more commonly used Markov decision process (MDP) in reinforcement learning. In LMDPs, the Bellman equations governing the value function are linear, which typically makes learning more efficient. In spite of being simpler than MDPs, LMDPs are surprisingly expressive and can be used to represent many reinforcement learning benchmarks. In particular, any MDP with deterministic actions can be converted into an LMDP. However, the large body of work on deep reinforcement learning largely ignores LMDPs as a representation. The goal of this project is to develop function approximation algorithms for LMDPs, e.g. deep neural networks. One way to do so is to study existing algorithms for MDPs and simplify them for the LMDP setting. |
|
|
Novel Algorithms for Centralized Multiagent Planning Centralized multiagent planning is the problem of computing a joint plan for a team of agents that collaborate to achieve a goal. This problem has many applications in the real world, e.g. ride sharing, logistic planning and manufacturing. The aim of this project is to develop novel algorithms for multiagent planning based on an existing approach that reduces centralized multiagent planning problems to exponentially smaller approximate AI planning problems that can be efficiently solved using state-of-the-art planning methods. The novel algorithms will be tested in challenging scenarios from the Multi-Agent Programming Contest. |
|
|
Expressive High-level Features for Generalized Plans An important breakthrough in the field of Automated Planning has been in the representation of solutions that not only solve one particular planning problem, but a possibly infinite class of planning problems. These solutions are named generalized plans, and they are represented as algorithms that branch and loop in a target language. These solutions generalize because of the branching and looping over a set of high-level features, so the main studies in the topic have explored the right representation of these features to capture generalized plans over huge set of planning classes (e.g., features in Description Logics, Qualitative Numeric Planning, Random-Access Machines, ...). Thus, in this project, we will analyze and study several feature representations to match the required expressivity to generalize over different classes of planning problems. |
|
|
Unbounded Best-First Generalized Planning Best-First Generalized Planning (BFGP) has been one of the most successful approaches to generalized planning, where solutions are expressed in the form of planning programs over pointers with a Random-Access Machine. Part of its success comes from the representation of solutions that allow to natively apply classical heuristic search approaches to generalized planning, while the other part is due to some design decisions performed by experts in the generalized planning problem (e.g., a bound in the maximum size of the solution). In this project, we will explore how to design an efficient search in the space of programs when such a bound does not exist, releasing the system from human expert knowledge in the given problem classes. |
|
|
Statistical Modeling of Online Discussions Online discussion is a core feature of numerous social media platforms and has attracted increasing attention for different and relevant reasons, e.g., the resolution of problems in collaborative editing, question answering and e-learning platforms, the response of online communities to news events, online political and civic participation, etc. This project aims to address, from a probabilistic modeling perspective, some existing challenges, both computational and social, that appear in platforms that enable online discussion. For example, how to deal with scalability issues, how to evaluate and improve the quality of online discussions, or how to generally improve social interaction such platforms. Generative models of online discussion threads: state of the art and research challenges |
|
|
Abstraction and Reasoning Challenge This project is about addressing the Abstraction and Reasoning Challenge (ARC), a kaggle competition consisting of large corpus of visual tasks that require abstraction and reasoning skills to be solved. Each ARC task contains 3-5 pairs of train inputs and outputs, and a test input for which you need to predict the corresponding output with the pattern learned from the train examples. The objective of this project to apply AI techniques (and possibly suggest novel ones) that combine search and learning for automated program synthesis that are developed in the AI/ML research group to address the challenge, or a part of it. |
|
|
PushWorld This project is about addressing the PushWorld challenge. PushWorld is a novel grid-world environment designed to test planning and reasoning with physical tools and movable obstacles. While recent advances in artificial intelligence have achieved human-level performance in environments like Starcraft and Go, many physical reasoning tasks remain challenging for computers. The PushWorld benchmark is a collection of puzzles that emphasize this challenge. PushWorld is available as an OpenAI Gym environment and in PDDL format in Github. The environment is suitable for research in classical planning, reinforcement learning, combined task and motion planning, and cognitive science. |
|
|
The League of Robot Runners Competition This project is about addressing the league of robot runners competition. The League of Robot Runners, sponsored by Amazon Robotics, is a competition series where participants tackle the core combinatorial challenges found in cooperative multi-robot coordination problems: robot dynamics, lifelong planning, task assignment, and real-time execution. Besides being intellectually stimulating, these challenges present themselves in high-impact industrial applications including warehouse logistics, transportation, and advanced manufacturing. |
|
|
Entropy-regularized reinforcement learning algorithms Entropy regularization is an extremely popular component of modern reinforcement learning methods. After several years of applying entropy regularization as a heuristic to drive exploration and improve optimization properties of RL algorithms, there has been lots of recent progress in providing solid theoretical foundations justifying this technique. Most recently, a sophisticated regularization technique has lead to the development of a principled RL algorithm, Q-REPS, that is entirely derived from first principles, yet can be implemented in large-scale environments essentially without any approximations to the theory. This project aims to progress the research on this method from two parallel directions: 1) Implement Q-REPS in large-scale environments and analyze its performance empirically and 2) analyze various properties of the algorithm that remain poorly understood. (Some important questions being: understanding the role of the regularization functions and finding alternatives, or studying the properties of the action-value functions returned by the algorithm.) The project requires strong mathematical skills, particularly in linear algebra and probability theory. Knowledge of convex analysis and optimization is a plus, but not absolutely necessary at the current stage. A unified view of entropy-regularized Markov decision processes |
|
|
Error averaging in approximate dynamic programming Error-propagation analysis of approximate dynamic programming methods is a classic research topic with several implications on reinforcement learning algorithms. The most well-known results consider basic DP algorithms like value iteration and policy iteration, with several new results added in recent years regarding regularized counterparts of these methods. One discovery on this front was the discovery that certain regularization choices result in an "error-averaging" property that ensures a benign propagation of policy evaluation errors: roughly speaking, instead of accumulating the absolute errors linearly, these schemes allow the cancellation of positive and negative errors. This project sets out to understand this phenomenon in more detail by decoupling the averaging effect from the regularization effects as much as possible, thus potentially enabling the development and analysis of more effective error-averaging RL algorithms. The project requires strong mathematical skills, particularly in linear algebra and probability theory. Knowledge of convex analysis and optimization is a plus, but not absolutely necessary at the current stage. Approximate Modified Policy Iteration and its Application to the Game of Tetris Leverage the Average: an Analysis of KL Regularization in RL |
|
|
Thompson sampling for sequential prediction Thompson sampling is one of the most well-studied algorithms for a class of sequential decision-making problems known as stochastic multi-armed bandit problems. In a stochastic multi-armed bandit problem, a learner selects actions in a sequential fashion, and receives a sequence of rewards corresponding to the chosen actions. A crucial assumption made in this problem is that the rewards associated with each action are random variables drawn independently from a fixed (but unknown) distribution. The goal of this project is to do away with this assumption and study Thompson sampling in non-stationary environments where the rewards may be generated by an arbitrary external process. Precisely, the project considers the framework of sequential prediction with expert advice, and aims to show theoretical performance guarantees for this algorithm and/or analyze its perormance empirically. The project requires strong mathematical skills, particularly in probability theory and multivariate calculus. Knowledge of convex analysis is a plus, but not absolutely necessary at the current stage. Learning to Optimize Via Posterior Sampling An Information-Theoretic Analysis of Thompson Sampling |
|
|
Better algorithms for online linear-quadratic control Linear-quadratic control is one of the most well-studied problem settings in optimal control theory: it considers control systems where states follow a linear dynamics, and the incurred costs are quadratic in the states and control inputs. In recent years, the problem of online learning in linear-quadratic control problems have received significant attention within the machine-learning community. One particularly interesting development is the formulation of the control problem as a semidefinite program (SDP), which allows the application of tools from online convex optimization. The present project aims to develop new algorithms for online linear quadratic control based on this framework by exploring the possibility of using regularization functions that make better use of the SDP geometry than existing methods based on online gradient descent. The project requires strong mathematical skills, particularly in multivariate calculus and linear algebra. Knowledge of control theory, convex analysis and optimization is a plus, but not absolutely necessary at the current stage. |
|
|
Concentration and generalisation under data dependencies Concentration inequalities are an essential probabilistic tool in the analysis of machine learning models, as they help control fluctuations of empirical quantities around their mean. A key application of these results is in deriving generalisation bounds for learning algorithms, which enable predictions of how well a trained model will perform on previously unseen data points. Most of the existing literature on the topic focuses on scenarios where the training dataset comprises independent data (sampled from an unknown distribution). However, this assumption is often unrealistic in practical situations where inter-dependencies exist among the training examples. Recently, there has been increasing interest in developing probabilistic tools to address such dependencies. The objective of this project is to extend certain classical concentration inequalities to cases involving dependent data, and to apply these results to obtain generalisation bounds suitable for this context. |
|
|
Structured uncertainty estimation for recurrent video restoration This thesis is about video restoration problems, such as noise removal and super-resolution. In the last 5 years, deep neural networks became the state of the art and have achieved remarkable advances in restoration quality. A problem of this type of methods is that -for the most part- we do not understand how they work: they are considered black box approaches for which it is difficult to provide guarantees on their performance or to characterize their failure modes. One way to address (at least partially) this issue is by estimating the uncertainty of the result. There are different ways to quantify uncertainty. We will consider the variance of the distribution of possible solutions. Some methods have been proposed that compute a per-pixel variance, which estimates the variance of each pixel of a restored image or video. These per-pixel variances fail to capture correlations between the values of different pixels. To that aim, a recent work proposes to estimate structured uncertainty in the context of single image restoration. The goal of this thesis is to extend this work to the case of video by using recurrent networks that process the video frame-by-frame. This requires propagating the structured uncertainty of previous frames, and updating it given the newly observed frame. |
|
|
Data Analysis in Education Technologies Several topics related to the application of AI and data analytics techniques to the design of systems that support teaching and learning (includes community, teaching and learning analytics, interactive dashboards, etc.) |
|
|
Ranking Attributes for Information Gain in Forests of Decision Trees (data science/machine learning related project) Decision trees are one of the most well-known techniques in machine learning, data science, analytics and data mining. They are transparent as they can be presented as rules for human understanding. Explainable AI, human-in-the-loop developments, and fair and ethical AI favour the transparency of decision trees. With the availability of big data, algorithms for constructing decision trees in a platform like MapReduce are a new challenge. This project consists of developing the parallelisation algorithms and their implementation for Hadoop when we consider a forest of decision trees. This implementation will be focused on the applications of the forest of decision trees on privacy-preserving data mining on online social networks (OLSN). We can provide references to recent literature on how the construction of a forest of decision trees is used to provide privacy alerts to users of OLSN. Another application is feature selection. |
|
|
Ethical Ai Agent The aim is to develop a demonstration of interaction by a human being with an artificial agent about ethical dilemmas and reason over ethical challenges. The agent shall apply several techniques to argue and explain ethical decisions, including game theory or dialogue with humans. Another possibility is deontic logic. The goal is to investigate practical debates between and artificial agents and humans regarding the alignment problem. Possibilities are to explore the use of generative AI and in particular, large language models. |
|
|
Verifiable AI The goal is to explore mechanisms of formal verification of agents' behaviour, particularly agents who can combine reasoning with operating over a state machine. Moreover, if the behaviour or the knowledge for reasoning is learned, behavioural properties should be verified regarding the behaviour. The aim is to create trustable AI systems because they have been formally verified even if they evolve by learning. The immediate applications are behaviours of autonomous vehicles, and particular aspects could be efficient negotiation of intersections. There is already evidence that artificial agents can negotiate intersections faster than humans and even minimise the requirement of traffic signals. However, there are challenges is mixed environments, such as humans and autonomous vehicles. The impact on mobility of artificial intelligence tools is the focus of this project. |
|
|
Audio-visual speech and singing voice separation Source separation is the automatic estimation of the individual isolated sources that make up the audio mixture. The goal of this project is to separate a human voice in a mixture by using both the audio and video modalities. We are interested in both speech and singing voice signals. The most direct applications of speech separation are speaker identification and speech recognition (for example, to create automatic captioning of videos). While some of the applications of singing voice separation are: automatic creation of karaoke, music transcription, or music unmixing and remixing. Leveraging visual and motion information from the target person's face is particularly useful when there are different voices present in the mixture. Deep neural networks that extract features from the video sequence will be explored and used in conjunction with an audio network in order to improve the audio source separation task by incorporating visual cues. |
|
|
Knowledge Graph Inference from Text One of the main problems of LLMs is the lack of control of the generated text. The industry cannot rely on them to develop Conversational Systems due to this lack of reliability and trustworthiness. One way to control the answers provided by Conversational Systems is to reduce the scope of the output by introducing a Knowledge Graph (KG) representing the task. This KG could be useful as a supervisor of the generated output. In this project we propose to explore the inference of KGs from text. In particular, we will use a corpus that was generated getting the domain knowledge from Wikidata KG (Vázquez et al, 2024). We aill attempt to reverse engineer it, i.e. to obtain triplets and their relations in a KG model. It will be evaluated as a post-processing technique and its integration with an LLM might also be explored. This Master thesis will be supervised By Prof. M. Inés Torres from the University of the Basque Country in Bilbao (north of Spain). Travel costs and a couple of short stays could be covered. |
|
|
Automatic labeling of emotions in speech One of the problems in speech emotion recognition (SER) is the ambiguity of the annotation procedure. Whether using crowd or expert annotation, the procedure is based on subjective perception experiments. This project aims to explore the feasibility of an annotation procedure based on recent audio and speech embeddings through prompt learning procedures. The result will be analyzed in terms of emotions and compared with classical approaches (Jing et al, 2019) (Jing at al, 2019). This Master thesis will be supervised By Prof. M. Inés Torres from the University of the Basque Country in Bilbao (north of Spain). Travel costs and a couple of short stays could be covered. Automatic speech discrete labels to dimensional emotional values conversion method |
|
|
Deep Neural Multilingual Lexical Simplification Lexical Simplification is a sub-task of Automatic Text Simplification that aims at replacing difficult words with easier to read (or understand) synonyms while preserving the information and meaning of the original text. This is a key task to facilitate reading comprehension to different target readerships such as foreign language learners, native speakers with low literacy levels or people with different reading impairments (e.g. dyslexic individuals). This master’s project aims at investigating novel techniques in Deep Learning and Natural Language Processing to improve current lexical simplification systems. The master student will have the opportunity to develop this research on an available multilingual dataset (English, Portuguese, Spanish) – TSAR 2022 Shared Task Dataset – annotated by human informants. More specifically, the annotations for a given complex word in a sentence is a list of suitable substitutes which could be used instead of the complex word. The candidate is expected to develop cross-lingual or multilingual techniques using available pre-trained models. In the recent TSAR 2022 shared task challenge, several teams participated proposing deep learning techniques (e.g. neural language models) to solve the problem. The candidate is expected to have some knowledge of Natural Language Processing (NLP) and experience with current deep learning paradigms in NLP. ALEXSIS: A Dataset for Lexical Simplification in Spanish. Lexical simplification benchmarks for English, Portuguese, and Spanish. |
|
|
From Sign Language to Spoken Language: Experiments in Deep Multimodal Translation In the era of mass communication and wide uptake of digital technologies amongst the general public, there still exist numerous communication barriers for the Deaf and Hard-of-Hearing (DHH) community. In spite of the recent advances in Machine Translation (MT) for spoken languages, automatic translation between spoken and Sign Languages or between Sign Languages remains a difficult problem. There is a great opportunity for research in Machine Translation (MT) to bridge the gap between written/spoken languages and Sign Languages. This master’s project aims at experimenting with current approaches in machine translation for sign languages with emphasis on the Sign Language - Spoken Language direction. The student will first experiment with available well-known datasets (e.g. German Sign Language PHOENIX14T dataset – video/text/glosses) exploring different models to extract patterns from videoframes and decode them to produce spoken text. After that, it is planned to apply Transfer Learning to produce models for less resourced SLs (e.g. Spanish or Catalan Sign Language). The candidate is expected to have some knowledge of Natural Language Processing (NLP) and experience with current deep learning paradigms in NLP. Knowledge of image processing is highly desirable. |