Search Results

Documents authored by Rossi, Francesca

Document
Invited Talk
DOI: 10.4230/LIPIcs.CP.2024.2
Thinking Fast and Slow in AI: A Cognitive Architecture to Augment Both AI and Human Reasoning (Invited Talk)

Authors: Francesca Rossi

Published in: LIPIcs, Volume 307, 30th International Conference on Principles and Practice of Constraint Programming (CP 2024)

Abstract
AI systems are very useful in practically every sector, but they also have several limitations, mostly related to the lack of reasoning capabilities. According to the fast and slow thinking theory of human decision making, we can say that data-driven AI, including generative AI, are providing fast thinking capabilities, but they do not have slow thinking ones. Existing cognitive theories of human decision making, such as the thinking fast and slow theory, can provide insights on how to advance AI systems towards some of these capabilities. In this talk I will present a general architecture, called SOFAI, that is based on fast/slow solvers and a meta-cognitive component that provides a centralized governance of the solvers. I will describe two instances of this architecture, for constrained grid navigation and planning, showing experimentally that SOFAI generates better decisions than each of the individual solvers. Emerging behavior related to adaptability, skill learning, and cognitive control are also showed in the analysis of SOFAI’s behavior. I will also describe how the thinking fast and slow theory can help design a value-based human-machine collaborative decision environment.
Cite as

Francesca Rossi. Thinking Fast and Slow in AI: A Cognitive Architecture to Augment Both AI and Human Reasoning (Invited Talk). In 30th International Conference on Principles and Practice of Constraint Programming (CP 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 307, p. 2:1, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{rossi:LIPIcs.CP.2024.2,
  author =	{Rossi, Francesca},
  title =	{{Thinking Fast and Slow in AI: A Cognitive Architecture to Augment Both AI and Human Reasoning}},
  booktitle =	{30th International Conference on Principles and Practice of Constraint Programming (CP 2024)},
  pages =	{2:1--2:1},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-336-2},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{307},
  editor =	{Shaw, Paul},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2024.2},
  URN =		{urn:nbn:de:0030-drops-206874},
  doi =		{10.4230/LIPIcs.CP.2024.2},
  annote =	{Keywords: Artificial Intelligence, Meta-reasoning}
}
Document
Invited Paper
DOI: 10.4230/LIPIcs.CONCUR.2016.2
Ethical Preference-Based Decision Support Systems (Invited Paper)

Authors: Francesca Rossi

Published in: LIPIcs, Volume 59, 27th International Conference on Concurrency Theory (CONCUR 2016)

Abstract
The future will see autonomous intelligent systems acting in the same environment as humans, in areas as diverse as driving, assistive technology, and health care. Think of self-driving cars, companion robots, and medical diagnosis support systems. Also, humans and machines will often need to work together and agree on common decisions. Thus hybrid collective decision making systems will be in great need. In these scenarios, both machines and collective decision making systems should follow some form of moral values and ethical principles (appropriate to where they will act but always aligned to humans'). In fact, humans would accept and trust more machines that behave as ethically as other humans in the same environment. Also, these principles would make it easier for machines to determine their actions and explain their behavior in terms understandable by humans. Moreover, often machines and humans will need to make decisions together, either through consensus or by reaching a compromise. This would be facilitated by shared moral values and ethical principles. In this paper we introduce some issues in embedding morality into intelligent systems. A few research questions are defined, with the hope that the discussion raised by the questions will shed some light onto the possible answers.
Cite as

Francesca Rossi. Ethical Preference-Based Decision Support Systems (Invited Paper). In 27th International Conference on Concurrency Theory (CONCUR 2016). Leibniz International Proceedings in Informatics (LIPIcs), Volume 59, pp. 2:1-2:7, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2016)

Copy BibTex To Clipboard

@InProceedings{rossi:LIPIcs.CONCUR.2016.2,
  author =	{Rossi, Francesca},
  title =	{{Ethical Preference-Based Decision Support Systems}},
  booktitle =	{27th International Conference on Concurrency Theory (CONCUR 2016)},
  pages =	{2:1--2:7},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-017-0},
  ISSN =	{1868-8969},
  year =	{2016},
  volume =	{59},
  editor =	{Desharnais, Jos\'{e}e and Jagadeesan, Radha},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CONCUR.2016.2},
  URN =		{urn:nbn:de:0030-drops-61870},
  doi =		{10.4230/LIPIcs.CONCUR.2016.2},
  annote =	{Keywords: preferences, decision making, multi-agent systems}
}
Document
DOI: 10.4230/DagSemProc.07431.1
07431 Abstracts Collection – Computational Issues in Social Choice

Authors: Ulle Endriss, Jérôme Lang, Francesca Rossi, and Tuomas Sandholm

Published in: Dagstuhl Seminar Proceedings, Volume 7431, Computational Issues in Social Choice (2007)

Abstract
From the 21st to the 26th of October 2007, the Dagstuhl Seminar 07431 on ``Computational Issues in Social Choice'' was held at the International Conference and Research Center (IBFI), Schloss Dagstuhl. During the seminar, several participants presented their recent research, and ongoing work and open problems were discussed. The abstracts of the talks given during the seminar are collected in this paper. The first section summarises the seminar topics and goals in general. Links to full papers are provided where available.
Cite as

Ulle Endriss, Jérôme Lang, Francesca Rossi, and Tuomas Sandholm. 07431 Abstracts Collection – Computational Issues in Social Choice. In Computational Issues in Social Choice. Dagstuhl Seminar Proceedings, Volume 7431, pp. 1-19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2007)

Copy BibTex To Clipboard

@InProceedings{endriss_et_al:DagSemProc.07431.1,
  author =	{Endriss, Ulle and Lang, J\'{e}r\^{o}me and Rossi, Francesca and Sandholm, Tuomas},
  title =	{{07431 Abstracts Collection – Computational Issues in Social Choice}},
  booktitle =	{Computational Issues in Social Choice},
  pages =	{1--19},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2007},
  volume =	{7431},
  editor =	{Ulle Endriss and J\'{e}r\^{o}me Lang and Francesca Rossi and Tuomas Sandholm},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.07431.1},
  URN =		{urn:nbn:de:0030-drops-12736},
  doi =		{10.4230/DagSemProc.07431.1},
  annote =	{Keywords: Computational social choice, voting theory, fair division, mechanism design, coalition formation, complexity theory, preference representation, algorithms}
}
Document
DOI: 10.4230/DagSemProc.07431.2
07431 Executive Summary – Computational Issues in Social Choice

Authors: Ulle Endriss, Jérôme Lang, Francesca Rossi, and Tuomas Sandholm

Published in: Dagstuhl Seminar Proceedings, Volume 7431, Computational Issues in Social Choice (2007)

Abstract
Computational social choice is an interdisciplinary field of study at the interface of social choice theory and computer science, with knowledge flowing in either direction. On the one hand, computational social choice is concerned with importing concepts and procedures from social choice theory for solving questions that arise in computer science and AI application domains. This is typically the case for managing societies of autonomous agents, which calls for negotiation and voting procedures. On the other hand, computational social choice is concerned with importing notions and methods from computer science for solving questions originally stemming from social choice, for instance by providing new perspectives on the problem of manipulation and control in elections. This Dagstuhl Seminar has been devoted to the presentation of recent results and an exchange of ideas in this growing research field.
Cite as

Ulle Endriss, Jérôme Lang, Francesca Rossi, and Tuomas Sandholm. 07431 Executive Summary – Computational Issues in Social Choice. In Computational Issues in Social Choice. Dagstuhl Seminar Proceedings, Volume 7431, pp. 1-3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2007)

Copy BibTex To Clipboard

@InProceedings{endriss_et_al:DagSemProc.07431.2,
  author =	{Endriss, Ulle and Lang, J\'{e}r\^{o}me and Rossi, Francesca and Sandholm, Tuomas},
  title =	{{07431 Executive Summary – Computational Issues in Social Choice}},
  booktitle =	{Computational Issues in Social Choice},
  pages =	{1--3},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2007},
  volume =	{7431},
  editor =	{Ulle Endriss and J\'{e}r\^{o}me Lang and Francesca Rossi and Tuomas Sandholm},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.07431.2},
  URN =		{urn:nbn:de:0030-drops-12749},
  doi =		{10.4230/DagSemProc.07431.2},
  annote =	{Keywords: Computational social choice, voting theory, fair division, mechanism design, coalition formation, complexity theory, preference representation, algorithms}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact