Thesis offers

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:

1. The computation of the partition function is NP-hard, involving an  exponential sum of terms
2. The exact computation of the derivative of the log-likelihood is  also NP-hard, since it contains the derivative of the partition function

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:

1. - Mechanisms to control the learning process: www.lsi.upc.edu/~eromero/Publications/Downloads/2018-tnnls-stopcritRBM.pdf
2. Better approximations of the derivative of the log-likelihood: http://www.lsi.upc.edu/~eromero/Publications/Downloads/2019-nn-weightedCD.pdf
3. Efficient approximation of the partition function (work in progress)

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 (eromero@cs.upc.edu).

This is precisely why companies such as Google have invested a lot of resources on exploring applications of GNN, some of which are as mediatic as Alpha Fold (recently solving the Protein-Folding problem), or used by Goolge Maps to make predictions of the expected traffic of a road. In this regard, the goal of this thesis is to continue investigating about the potential of GNNs when applied to the field of Computer Networks. Our goal is to provide GNN-based solutions that make computer networks run more autonomously and in a more efficient way.

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".

The thesis would be a continuation of a previous master thesis in which we have built a baseline system that is able to extract simple rules whose elements are generalized codes. However, we want to extend this system to deal with sequence patterns as the ones mentioned before, eventually composed by sentences in Natural Language.

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 thesis is to enable the application of Deep Reinforcement Learning techniques for optimization problems in very large and complex scenarios. Inspired by the last related work from OpenAI (https://openai.com/blog/evolution-strategies/), we will explore time-efficient alternatives to train a Graph Neural Network based DRL agent on large optimization scenarios in a reasonable amount of time.

Please answer the internship offer to apply for this TFG:
https://borsapractiques.fib.upc.edu/ca/ofertes/oferta/316

In order to obtain a thorough understanding of the professional profile of a candidate, we need to carry out an interview that is adapted to his/her particular context. With this project, we intend to leverage Deep Learning and equip our Chatbot with the ability to generate new questions based on the conversation history and a goal.

Given the conversation history up to the step t of an interview, a NER algorithm (Named Entity Recognition) will identify the entities present in the candidate's reply, allowing us to define the information we want to obtain in the next utterance exchange (the goal). The NLG model (Natural Language Generation), which is the object of research of this project, would take as an input both the conversation history up to step t and the specific entities that we intend to identify in the next step, in order to generate the next utterance and carry on with the conversation.

The above defined framework is inspired in GoChat (https://arxiv.org/pdf/2005.11729.pdf), a chatbot trained using Reinforcement Learning to endow its utterances and overarching conversations with a goal.

A more detailed description of the project can be found in

https://www.cs.upc.edu/~eromero/Downloads/Retina-TFM-Project-01.pdf

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 (eromero@cs.upc.edu).

Typically, these studies identify over- or under-expression of a given biomarker associated with poor or good patient outcome. Identifying biomarkers is fundamental to improve disease clinical management.

The goal of the project would be to identify genes ("Modulators") that in combination/by interacting with a "cancer driver gene" augment or reduce the risk of tumor progression. Tasks will be focused into exploring advanced technologies based on electronic health records to improve the results obtained with classical signal processing methods.

To this aim the main steps of the proposal are:

· To apply unsupervised clustering techniques in order to identify breast-cancer patterns in terms of the activation or no of most relevant gene pathways.

· To apply survival analysis: Cox regression analysis and Kaplan-Meier curves.

· Based on previous steps, to provide a patient predictor model of relapse time and / or death time counting from the first diagnosis.

· To apply non-linear models to the Cox regression survival analysis in order to improve the previous classical outcomes.

Please answer the internship offer to apply for this TFM:
 https://borsapractiques.fib.upc.edu/ca/ofertes/oferta/298

You are going to develop NLP techniques to match retail products based on free-text descriptions and structured attributes.
For example, your models will learn that "iPhone 8 64GB" and "iPhone 6 8GB" are not the same product even though the string only differs in 1 character, but "Camiseta oficial FC Barcelona temporada 2021-2022" and "Camiseta Nike FC Barcelona Primera Equipación 2021-2022" are indeed the same.

You will have to

• Handle real world data, typically in csv/xls or json format, and import it into an analysis environment
• Develop NLP models using techniques such as Document Embedding, Document Distances, and Semantic Interpretations
• Work locally with your machine, then merge the data and new code into our master branch.
• Produce reports and documentation with your findings

 The goal of this thesis is to enable the application of Deep Reinforcement Learning techniques for optimization problems in very large and complex scenarios, in this case Data Center Networks. Inspired by the last related work from OpenAI (https://openai.com/blog/evolution-strategies/), we will explore time-efficient alternatives to train a Graph Neural Network based DRL agent on large optimization scenarios in a reasonable amount of time.

The goal of this thesis is to enable the application of Deep Reinforcement Learning techniques for optimization problems in very large and complex scenarios, in this case LEO satellite communication networks. Inspired by the last related work from OpenAI (https://openai.com/blog/evolution-strategies/), we will explore time-efficient alternatives to train a Graph Neural Network based DRL agent on large optimization scenarios in a reasonable amount of time.