Logic-Based Technologies for Intelligent Systems: State of the Art and Perspectives

Calegari, Roberta; Ciatto, Giovanni; Denti, Enrico; Omicini, Andrea

doi:10.3390/info11030167

Cited by 39 publications

(22 citation statements)

References 164 publications

(110 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI systems nowadays work on large amounts of data, learning from experience and making predictions with the goal of supporting human decisions or taking autonomous ones-applications range from clinical decision support to autonomous driving and predictive policing [61]. Nevertheless, concerns about the intentional and unintentional negative consequences of AI systems are legitimate, as well as ethical and legal concerns, mostly related to darkness and opaqueness of AI decision algorithm.…”

Section: Discussionmentioning

confidence: 99%

On the integration of symbolic and sub-symbolic techniques for XAI: A survey

Calegari

Ciatto

Omicini

2020

Self Cite

View full text Add to dashboard Cite

The more intelligent systems based on sub-symbolic techniques pervade our everyday lives, the less human can understand them. This is why symbolic approaches are getting more and more attention in the general effort to make AI interpretable, explainable, and trustable. Understanding the current state of the art of AI techniques integrating symbolic and sub-symbolic approaches is then of paramount importance, nowadays—in particular in the XAI perspective. This is why this paper provides an overview of the main symbolic/sub-symbolic integration techniques, focussing in particular on those targeting explainable AI systems.

show abstract

Section: Discussionmentioning

confidence: 99%

On the integration of symbolic and sub-symbolic techniques for XAI: A survey

Calegari

Ciatto

Omicini

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…MAS should be aligned with multidisciplinary fields, in which areas such as social science, psychology, and cognitive science could be integrated and studied together, complementing each other and contributing to study human factors [21]. About this topic, logic-based [22] and cognitive sciences approaches have contributed significantly to the development of MAS [23] that have been increasingly used, allowing simulations involving numerous agents are computationally viable [24].…”

Section: Multiagent Systems and Simulation Of Behaviormentioning

confidence: 99%

Using the Myers-Briggs Type Indicator (MBTI) for Modeling Multiagent Systems

Braz¹,

Sichman²

2022

RITA

View full text Add to dashboard Cite

The formation of high-performance teams has been a constant challenge for organizations, which despite considering human capital as one of the most important resources, it still lacks the means to allow them to have a better understanding of several factors that influence the formation of these teams. In this sense, studies also demonstrate that teamwork has a significant impact on the results presented by organizations, in which human behavior is highlighted as one of the main aspects to be considered in the building of work teams. The Myers-Briggs Type Indicator seeks to classify the behavioral preferences of individuals around eight characteristics, which grouped as dichotomies, describe different psychological types. With it, researchers have sought to expand the ability to understand the human factor, using strategies with multiagent systems that, through experiments and simulations, using computer resources, enable the development of artificial agents that simulate human actions. In this work, we present an overview of the research approaches that use MBTI to model agents, aiming at providing a better knowledge of human behavior. Additionally, we make a preliminary discussion of how these results could be explored in order to advance the studies of psychological factors' influence in organizations' work teams formation.

show abstract

“…Logic programming (LP) technologies (e.g., Prolog) enable users -and potentially agents -to encode their knowledge into logic facts and rules, which may then be queried via logic solvers [27]. Accordingly, by endowing agents with adequate LP technologies, they can autonomously exploit inference when required [27].…”

Section: Mechanisms For Imaginationmentioning

confidence: 99%

Towards Explainable Visionary Agents: License to Dare and Imagine

Ciatto

Najjar

Calbimonte

et al. 2021

Explainable and Transparent AI and Multi-Agent Systems

Self Cite

View full text Add to dashboard Cite

Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying on Machine Learning (ML), symbolic reasoning, and the ability of their developers for tailoring smart behaviors to specific application domains. However, to forecast the evolution of all possible scenarios is unfeasible. Thus, intelligent agents should autonomously/creatively adapt to the world's mutability. This paper investigates the meaning of imagination in the context of cognitive agents. In particular, it addresses techniques and approaches to let agents autonomously imagine/simulate their course of action and generate explanations supporting it, and formalizes thematic challenges. Accordingly, we investigate research areas including: (i) reasoning and automatic theorem proving to synthesize novel knowledge via inference; (ii) automatic planning and simulation, used to speculate over alternative courses of action; (iii) machine learning and data mining, exploited to induce new knowledge from experience; and (iv) biochemical coordination, which keeps imagination dynamic by continuously reorganizing it.

show abstract

Logic-Based Technologies for Intelligent Systems: State of the Art and Perspectives

Cited by 39 publications

References 164 publications

On the integration of symbolic and sub-symbolic techniques for XAI: A survey

On the integration of symbolic and sub-symbolic techniques for XAI: A survey

Using the Myers-Briggs Type Indicator (MBTI) for Modeling Multiagent Systems

Towards Explainable Visionary Agents: License to Dare and Imagine

Contact Info

Product

Resources

About