Starting in March 2023, the Hybrid Intelligence Center is looking to fill the following PhD student and postdoc vacancies. Projects marked with a star are currently open for applications.
Supervisor: Andrew Yates, University of Amsterdam
Co-supervisor: Piek Vossen, Vrije Universiteit Amsterdam
Short description:
We will support the investigation step of the scientific method cycle through a scientific assistant that helps identify relevant literature (at the document level) and helps pinpoint relevant information within this literature.
Supervisor: Annette ten Teije, Vrije Universiteit Amsterdam
Co-supervisor: Herke van Hoof, University of Amsterdam
Short description:
We will support the investigation step of the scientific method cycle through a scientific assistant that helps identify relevant literature (at the document level) and helps pinpoint relevant information within this literature.
Supervisor: Antske Fokkens, Vrije Universiteit van Amsterdam
Co-supervisor: Shihan Wang, Utrecht University
Short description:
In linguistic tasks, not all errors are equal. Which errors are more important than others changes according to how a model will be used. We will investigate how to use reinforcement learning to guide models to a specific behavior in computational linguistic tasks, prioritizing some forms of correctness over others. Shihan Wang (UU)
Supervisor: Catha Oertel, Technical University Delft
Co-supervisor: Piek Vossen, Vrije Universiteit Amsterdam
Short description:
Successful communication within a multi-party meeting depends on the creation of a common ground between interaction partners: what is relevant for oneself, what is relevant for the interaction partner(s). We focus on memory creation based on affective responses to conversational instances and their relation to real-world objects supporting the interaction.
Supervisor: Joost Broekens & Aske Plaat, University of Leiden
Co-supervisor: Kim Baraka, Vrije Universiteit Amsterdam
Short description:
How can we use affective signals grounded in the learning process of an RL agent as feedback to a human teacher to close the teacher learner loop? Emotion simulation and means of expression on robots and agents studied in the context of human-agent interaction.
Supervisor: Daniel Balliet, Vrije Universiteit Amsterdam
Co-supervisor: vacancy
Short description:
CoDa is the first databank to represent an entire field of studies in the social sciences (human cooperation) in a machine-readable way which can be searched to select studies for on-demand meta-analysis. We will generalize CoDa to factors from economics (e.g., altruism, trust), sociology (e.g., social capital), and clinical psychology (i.e., treatments of depression), we will develop queries that can produce on-demand meta-analyses, and develop an interactive technique to create queries and update meta-analyses (e.g., text of the manuscript).
Supervisor: Davide Grossi, University of Groningen
Co-supervisor: Pradeep Murukannaiah, Technical University Delft
Short description:
We will develop a methodology for supporting participatory democratic decision making online. The methodology should support (1) users in participating in online democratic deliberation and reflecting on the alignment between their choices and values, (2) policy makers in aggregating users’ choices and opinions in a principled and transparent manner.
Supervisor: Erik Bekkers, University of Amsterdam
Co-supervisor: Daniel Pelt, University of Leiden
Short description:
We will develop techniques for collaborative human-computer image annotation of training sets for deep learning tasks. Our techniques will suggest relevant annotations to the human annotator, will indicate inconsistencies in the human annotations, and will use concepts from geometric deep learning to handle shapes of image annotations.
Supervisor: Frans A. Oliehoek, Technical University Delft
Co-supervisor: Jan-Willem vd Meent, University of Amsterdam
Short description:
We will investigate how Bayesian methods can be used in multi-agent reinforcement learning (MARL) as a way to infer models of human partners, in order to collaborate with them more effectively.
Supervisor: Hayley Hung, Technical University Delft
Co-supervisor: Dan Balliet, Vrije Universiteit Amsterdam
Short description:
We know that there are critical moments in social interactions that determine whether to select someone as a collaborative partner. The goal of this project is to bridge the artificial perception and action loop by considering the idea of building a HI Social Guru. This is carried out through (i) goal setting, (ii) enlightenment and (iii) empowerment via the HI Social Guru. The important thing about a Guru is that they assist humans in self-reflection in social settings without needing to interfere directly (synchronously) with the interaction. That is, they provide wisdom and enlightenment asynchronously from the interaction.
Supervisor: Ilaria Tiddi, Vrije Universiteit Amsterdam
Co-supervisor: Bart Verheij, University of Groningen
Short description:
How can we use large-scale structured data harvested from the (structured, machine-readable) web in argumentation about complex hypotheses?
Supervisor: Kim Baraka, Vrije Universiteit Amsterdam
Co-supervisor: Dirk Heylen, University of Twente
Short description:
How can an AI system foster synergetic exchange with a human during a creative process? We will develop a collection of novel algorithmic tools that will allow a human+AI system to achieve an improved outcome when collaborating together as opposed to when engaging in a creative process by themselves.
Supervisor: Max van Duijn, University of Leiden
Co-supervisor: Rineke Verbrugge, University of Groningen
Short description:
The aim is to study how common ground emerges, and how such common ground can support Theory of Mind, using agent-based modeling of a collaborative game and lab experiments in which humans and AI agents play that same game.
Supervisor: dr. Mike Ligthart, Vrije Universiteit Amsterdam
Co-supervisor: dr. Shenghui Wang, University of Twente
Short description:
Creating engaging and personalized content for sustained human-robot interactions over time, in our case between robots and children in an educational setting, is currently done entirely manually. We will develop a hybrid solution for interaction content generation, ranging from high-level content creation (e.g. robot personality, conversational goals and narratives, and dialog templates) to mini-dialog generation (e.g. dynamically integrate fragments of high-level narratives and robot’s personal stories with child-robot conversational history into individual utterances).
Supervisor: Piek Vossen, Vrije Universiteit Amsterdam
Co-supervisor: Catha Oertel, Technical University Delft
Short description:
In a collaborative interactive setting between humans and agents, it is crucial that their memories get partially aligned to make decisions on agreed information but also to know how differences across memories can be leveraged. In this project, we create conversational models for agents to achieve such alignment, which is essential to establish shared conceptualizations for memories in a Theory of Mind (ToM) model.
Supervisor: Pinar Yolum, University of Utrecht
Co-supervisor: Pradeep Murukannaiah, Technical University Delft
Short description:
We will investigate how the notion of consent can be used as an abstraction to capture and facilitate interactions among multiple humans and AI agents in realizing hybrid intelligence. How can consent be formally represented? What are the types of consent and how can they be inferred? When and how should an agent request consent?
Supervisor: Roel Dobbe, Technical University Delft
Co-supervisor: Maarten de Rijke, University of Amsterdam
Short description:
We will develop new methodologies to design for the emergent nature of hybrid intelligent systems. We will develop formal abstractions for the analysis and design of the dynamics of hybrid intelligent systems. These will inform practical design. methodologies that can enforce important emergent properties such as safety or justice in the emergent system dynamic
Supervisor: Victor de Boer, Vrije Universiteit Amsterdam
Co-supervisor: Shenghui Wang, University of Twente
Short description:
We will investigate interactive methods for eliciting annotations of heritage objects by users from a varied background (cultural, geographical, gender, a.o.). We will investigate methods to acquire this diverse knowledge through a variety of modalities (dialogue systems, VR, and others) combined with diversity-preserving annotation and crowdsourcing methods.
Supervisor: Bart Verheij, University of Groningen
Co-supervisor: Silja Renooij, University of Utrecht
Short description:
Bayesian Networks are very specific in what they require in order to work correctly. Bringing them from an idealised world of pure statistics and probability theory, to the real world of missing data, counterfactual reasoning and human biases, brings about significant problems.
Supervisor: Birna van Riemsdijk, University of Twente
Co-supervisor: Victor de Boer, Vrije Universiteit Amsterdam
Short description:
We will develop a framework to support dialogues between a user and an agent. We want to make it possible for the agent to recognize when it is missing information so that this can then be communicated to the user. It must then also be possible to incorporate the input from the user into the agents knowledge base.
ASSOCIATE PROFESSOR (TENURE TRACK) IN HYBRID INTELLIGENCE
Vrije Universiteit Amsterdam
POSITION NOW CLOSED
Vrije Universiteit Amsterdam is looking for a new colleague at the associate professor level to strengthen the research in Hybrid Intelligence, who will be closely aligned with the national research programme on Hybrid Intelligence. Examples of relevant areas of expertise are conversational AI, formal argumentation, computational social choice theory, multi-agent systems, plan recognition, safe and explainable reinforcement learning, explainable AI, computational game theory, causality, common-sense reasoning and AI in game playing, among others. Do not hesitate to apply if you have another area of expertise beyond this indicative list that is relevant to the study of Hybrid Intelligence.