The fellowship recipient will join a team of experienced researchers in a project whose goal is to apply model reduction techniques to the problem of simulating large networks of realistic neuron models.  In particular the fellowship recipient is expected to be heavily involved with two of the project's tasks. 
The goals of these tasks include the following:
- to develop what are known as gray or black-box modeling strategies based on machine learning techniques. Such techniques do not assume structural knowledge of the modeled systems to be available or explored, and instead work with generic internal information as well as input output behavior obtained from an executable representation of the system
- to develop and analyse different automatic timestep control mechanisms for managing the time-domain simulation of such systems; such mechanisms must take advantage of the known or observable dynamics of the system and be based on variable timestep control algorithms

LAW-NLP aims to explore the use of natural language processing to help users understand and identify relevant Portuguese consumer laws that apply to their situation. To that end, the applicant will explore the use of semantic analysis (such as semantic role labelling), to enrich the Portuguese Consumer Law with a semantic representation, and further use this data to train Question-Answering Models and/or Chatbots.

Development of a case study on the application of an adaptive control algorithm for a coupled robot system.
Work plan:
1) Study of distributed optimal control based on games
2) Study of distributed adaptive control
3) Application of the previous methods to a coupled robot system interconnected through an elastic joint
4) Final conclusions and report

The candidate will work on Task 5 of the Cosmos project, namely on “Implementation and Evaluation”. The concrete task of the candidate will implement and evaluate algorithms to offer transactional guarantees for edge storage systems.

Development of advanced models for disaggregation and synthesis of time series data of distributed consumption and production; utilization of disaggregated time series to train new forecast models adapted to the dynamics typical of HV and MV consumption and production in order to significantly improve forecasts quality 72h ahead.

Utilization of disaggregated time series to train new forecast models adapted to the dynamics typical of HV and MV consumption and production to significantly improve forecasts quality 72h ahead; make the codes of predictive models available as open-source apps and monitor their integration on the Azure platform.

The candidate will work on the project SLICE, which aims to develop and validate an authoring-friendly framework for the creation of transparent social intelligent agents capable of being deployed as virtual characters in training simulations or games or used to drive the behaviour of social robots. This framework joins two until now disparate areas of artificial intelligence research, namely, social agent architectures and machine learning. In particular, the candidate will work on the Model and Dialog System components.

The selected candidate will be a member of the research project PassCert, which aims at building an open-source, proof-of-concept password manager that through the use of formal verification, is guaranteed to satisfy properties on data storage and password generation. PassCert is a research collaboration between researchers from INESC-ID Lisboa (PT), INESC TEC (PT), and Carnegie Mellon University (US).
The selected candidate will:
 1) Contribute to the development of the proof-of-concept verified password manager.
 2) Explore ways in which the data security of the password manager can improve.
 3) Investigate ways of formally verifying the data security properties identified.
 4) Actively participate in and contribute to PassCert's activities and regular meetings.

This scholarship will Investigate the generation and impact of creative AI explanation approaches, such as time-based visualisations and infographics, sound/music-based, in order to increase user engagement, understandability, and acceptance of AI explanations in the context of information manipulation. Social and psychological aspects will be taken into account in the aim of producing personalised XAI.

	1) Perform an extensive survey on techniques of testing, debugging, and repair quantum programs
	2) Develop a framework to do mutation testing and repair of quantum programs
	3) Empirically evaluate and compare algorithm against state-of-the-
	4) Publish a research paper

Develop artificial personas for automated UX testing of interactive systems. These personas should define different motivation and different strategies for the interaction with an environment under test. The personas will be implemented as AI agents combining ML and search and may include a cognitive affective model to drive the decisions.

The Contrafake project develops a news analysis tool that, given a news text, generates an information nutrition label that could help information consumers decide about the credibility of that news. INESC-ID aims to recruit one candidate with BSc degree to work on the development of the user interface for the tool. Candidates should have academic training and practice in mobile and web applications development (including browser extensions), human computer interaction and information visualization.