Languages follow many statistical regularities called laws. Perhaps the most popular example is Zipf's law for word frequencies, that relates the frequency of a word with its rank, but other laws have been formulated, such as the law of abbreviation, the law of meaning-distribution, the meaning-frequency law,...and so on (Zipf 1949). About 15 years ago, a family of optimization models was introduced to shed light on the origins of Zipf's law for word frequencies (Ferrer-i-Cancho & Solé 2003, Ferrer-i-Cancho 2005). In that family, language is modelled as a bipartite graph where words connect to meanings and a cost function is defined based on the structure of that graph. A simple Monte Carlo algorithm was used to minimize the cost function while the structure of the graph was allowed to vary. Recently, it has been shown how these models shed light on how children learn words (Ferrer-i-Cancho 2017). The aim of this project is to investigate new versions of these models (e.g., Ferrer-i-Cancho & Vitevitch 2018) in two directions: (1) Providing an efficient implementation of the optimization algorithm. (2) Comparing the statistical properties of the model against the statistical properties of natural communication systems.
In greater detail, the two directions consist of
(1) Providing an efficient implementation of the optimization algorithm. See Ferrer-i-Cancho and Solé (2003) and Ferrer-i-Cancho (2005) for further details about the algorithm. Evaluating the cost for a given bipartite graph from scratch has cost of the order of nm, where n is the number of words and m is the number of meanings. Decinding when to stop the optimizacion algorithm requires (nm)^2 evaluations of the cost function (in practice it had to be cut down to about nm due to computational costs). For these reasons, n and m have been kept small in previous studies compared to real values in fully fledged human language (e.g., n = m = 150 in Ferrer-i-Cancho and Solé 2003). This computational callenge would be solved applying different techniques, e.g., (a) parallelization (b) dynamic calculation (when changing a few cells of the adjacency matrix, the cost function should not be computed from scratch) and (c) heuristics to speed up the Monte Carlo scheme.
(2) Comparing the statistical properties of the model against the real statistical properties of human language (e.g., linguistics laws) and animal communication, including properties that have not been tested in previous research on these models. See Ferrer-i-Cancho (2018) for an overview of some of the statistical properties of real language that could be tested.
Depending on the personal interests of the student, the project can focus in one of the two directions.
It is possible to publish the results of the project in a research journal.
Ferrer-i-Cancho, R. & Solé, R. V. (2003). Least effort and the origins of scaling in human language. Proceedings of the National Academy of Sciences USA 100, 788-791.
Ferrer-i-Cancho, R. (2005). Zipf's law from a communicative phase transition. European Physical Journal B 47, 449-457.
Ferrer-i-Cancho, R. (2017). The optimality of attaching unlinked labels to unlinked meanings. Glottometrics 36, 1-16.
Ferrer-i-Cancho, R. & Vitevitch, M. S. (2018). The origins of Zipf's meaning-frequency law. Journal of the American Society for Information Science and Technology 69 (11), 1369-1379.
Ferrer-i-Cancho, R. (2018). Optimization models of natural communication. Journal of Quantitative Linguistics 25 (3), 207-237.
Zipf, G.K. (1949). Human behaviour and the principle of least effort. Cambridge (MA), USA: Addison-Wesley.
The master thesis consists of developing a framework for Group Recommender Systems and investigating the methods for generating recommendations to groups.
Most of the research on group recommendation investigated the core algorithms used for recommendation generation. Two different strategies have been mostly used for generating group recommendations: aggregating individual predictions into group predictions or aggregating individual models into group models. Differences among these strategies differ in the timing of data aggregation step.
In fact, the role of a group recommender system is to make suggestions that reflect the preferences of the group as a whole, while offering reasonable and acceptable options to individual group members. An important issue to be addressed in this kind of recommenders is how to reach consensus among members during and at the end of the recommendation process.
In this proposal, the focus will be on generating a group recommender framework that will be based on the well-known LibRec library. The main steps will be:
Boltzmann Machines are probabilistic models developed in 1985 by
D.H. Ackley, G.E. Hinton and T.J. Sejnowski. In 2006, Restricted
Boltzmann Machines (RBMs) were used in the pre-training step of
several successful deep learning models, leading to a new renaissance
of neural networks and artificial intelligence.
In spite of their nice mathematical formulation, there are a number of
issues that are hard to compute:
Therefore, in practice we have to approximate both the computation of
the probabilities and several components of the learning process
itself. These drawbacks have prevented RBMs to show their real
potential as truly probabilistic models.
Currently, we are working on trying to improve several of the unsolved
issues related to RBMs:
These works have opened new lines of research, some of which can be
the topic of a Master's Thesis. The scope and degree of depth of the
work can be adapted to the estimated times to complete the Thesis. For
further details, contact Enrique Romero (firstname.lastname@example.org).
Study and implement deep learning based recommendation methods such as Neural collaborative filtering or Neural matrix factorization (DeepFM), and applied in a real dataset of sales of an online retail shoe company (Camper) for recommending products to clients
There are several papers in Deep learning based Recommender systems that I will provide, in particular Multilayer Perceptron (MLP) based recommendation by collaborative filtering and contents based methods . The goal is to build a (deep) neural network recommendation system based on user's history of buys. I have a large dataset of history of sales of company Camper through its digital platform which will serve as real test scenarios.
This project aims to analyze the prediction capability of Optical Coherence Tomography Angiography (OCTA) images for Diabetes Mellitus (DM) and Diabetic Retinopathy (DR,) in a large high-quality image dataset from previous research projects carried out in the field of Ophthalmology (Fundacio¿ La Marato¿ TV3, Fondo Investigaciones Sanitarias, FIS). OCTA is a newly developed, non-invasive, retinal imaging technique that permits adequate delineation of the perifoveal vascular network. It allows the detection of paramacular areas of capillary non perfusion and/or enlargement of the foveal avascular zone (FAZ), representing an excellent tool for assessment of DR.
A more detailed description of the project can be found in
The project is proposed in collaboration with Javier Zarranz Ventura
(Institut Clínic d'Oftalmologia, ICOF, Hospital Clínic de Barcelona, and
Institut d'Investigacions Biomèdiques August Pi I Sunyer, IDIBAPS),
which would provide a large annotated database to develop the project. For further information, please contact Alfredo Vellido (avellido@cs.
upc.edu) or Enrique Romero (email@example.com).
Machine Learning with TinyML TinyML aims to do machine learning on microcontrolers. Microcontrolers are sometimes the only hardware choice when the power supply is limited, e.g. in for battery-operated applications. Just one application areas are "wildlife" observation, such as: https://mybirdbuddy.com/ https://opencollar.io/ Arduino Uno and Mega boards are well known for all kinds of hobbyist microcontroler projects, but there is another kind of more powerful 32 bit microcontrolers and develpment boards, which are able to run machine learning applications. To get the first information on this topic you can have a look at TensorFlow Lite for Microcontrollers: https://www.tensorflow.org/lite/microcontrollers We have a couple of the mentioned boards like the Arduino Nano 33 BLE Sense, STM32F746 Discovery kit and Espressif ESP32 microcontrolers which can be used for this project. The project will in a first phase explore with practically example applications the topic and do some reading to get a basic understanding of the background. Then the second phase can be shaped accroding to the interest: The project could either develop and deploy a specific applications of interest or focus on analyzing and experimenting a specific step of the TinyML machine learning (ML) pipeline which starts at data acquisition and building a machine learning model until doing the deployment and evaluating the application. Other ideas can be suggested, also the integrating an ML-component running on a microcontroler with network connectivity into a distributed application can be discussed. You can find several TinyML examples in Tensorflow, medium or towardsdatascience webs, which people have already tried with code in github repositories e.g. https://codelabs.developers.google.com/codelabs/ai-magicwand/#0 https://www.digikey.es/en/maker/projects/intro-to-tinyml-part-1-training-a-model-for-arduino-in-tensorflow/8f1fc8c0b83d417ab521c48864d2a8ec https://towardsdatascience.com/tensorflow-meet-the-esp32-3ac36d7f32c7
In recent years the volume of information available electronically has increased exponentially, coining the term Big Data to refer to this phenomenon. The medical domain is an area in which the number of documents generated by the centers for patient primary care constantly increases. However, a bottleneck is generated because processing these documents requires specialized personnel craftly performing tasks. In the framework of TADIAMED research project, we are developing a set of processors that allow automatic analysis of medical texts taking into account criteria of robustness, high precision and coverage. In particular, this thesis would aim at the acquisition of patterns of clinical behavior from medical records, represented as semantic graphs using Neo4J database.
The medical records of each patient contain textual information about the clinical evolution of the patient (including drugs, chemicals, diseases, symptoms and body parts). This corpus has already been represented in a structured format as a set of semantic graphs, using Neo4J graph database.
This thesis would aim at the acquisition of patterns of clinical behavior from these graphs. These patterns would be specifically devoted to provide help in diagnosis to the medical community in primary care. For example, we can get to automatically infer that a certain drug has a previously unknown side effect, or that patients suffering from a certain disease develop certain symptoms in a certain period of time. A simple example of pattern might be "patient has fever and is prescribed ibuprofen -(after x days) - patient has fever and soreness - (after y days) - patient has fever and breathing difficulty -> patient diagnosed with COVID".
Since we have an annotated corpus of medical records, the project might use supervised and semi-supervised machine learning techniques as well as more standard data mining techniques.
The goal of this project is to analyze and mitigate bias in collaborative filtering recommender systems.
Recommender systems analyze the behavior of the users and their preferences, to learn patterns and understand what might be interesting to suggest them. Natural imbalances in the data (e.g., in the amount of observations for a subset of popular items) might be embedded in the patterns. As a consequence, the produced recommendations exacerbate these imbalances, thus strengthening inequalities and generating biases . When these imbalances are associated to sensitive attributes of the users (e.g., gender or race), this might have negative societal consequences, such as unfairness . Unfairness might affect all the stakeholders involved in a recommender system, such as the users (when the minority receives systematically worse recommendations), or the content providers (when the items offered by a group of providers are exposed less than those of their counterpart) .
The goal of this project is to analyze and mitigate bias in recommender systems. To do it, we will consider state-of-the-art recommender systems, covering both model- and memory -based approaches and point-wise and pair-wise algorithms.
 Himan Abdollahpouri, Gediminas Adomavicius, Robin Burke, Ido Guy, Dietmar Jannach, Toshihiro Kamishima, Jan Krasnodebski, and Luiz AugustoPizzato. 2020. Multistakeholder recommendation: Survey and research directions.User Model. User-Adapt. Interact.30, 1 (2020), 127¿158. https://doi.org/10.1007/s11257-019-09256-1
 Ludovico Boratto, Gianni Fenu, and Mirko Marras. 2019. The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses.InAdvances in Information Retrieval - 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14-18, 2019, Proceedings, Part I(Lecture Notes in Computer Science, Vol. 11437), Leif Azzopardi, Benno Stein, Norbert Fuhr, Philipp Mayr, Claudia Hauff, and Djoerd Hiemstra (Eds.).Springer, 457¿472. https://doi.org/10.1007/978-3-030-15712-8_30
 Sara Hajian, Francesco Bonchi, and Carlos Castillo. 2016. Algorithmic Bias: From Discrimination Discovery to Fairness-aware Data Mining.InProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016, Balaji Krishnapuram, Mohak Shah, Alexander J. Smola, Charu C. Aggarwal, Dou Shen, and Rajeev Rastogi (Eds.). ACM, 2125¿2126.https://doi.org/10.1145/2939672.2945386
 Francesco Ricci, Lior Rokach, and Bracha Shapira. 2015. Recommender Systems: Introduction and Challenges. InRecommender Systems Handbook,Francesco Ricci, Lior Rokach, and Bracha Shapira (Eds.). Springer, 1¿34. https://doi.org/10.1007/978-1-4899-7637-6_