Information Theory and Cognitive Agents
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".
Deadline for manuscript submissions: closed (15 December 2023) | Viewed by 4662
Special Issue Editors
Interests: artificial Intelligence; machine learning; computational intelligence; computational neuroscience; cognitive science
Special Issues, Collections and Topics in MDPI journals
Interests: artificial life; artificial intelligence; information theory; minimally cognitive agents; embodiment
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Cognitive agents play a critical role in current Artificial Intelligence research. By mimicking distinguishing features of human cognition, such as both short- and long-term-oriented behavior, whether goal-seeking, explorative or maintaining state, whether reactive or based on reasoning and planning, they share the cycle of gathering, storing, and processing information to make decisions and act appropriately in their environment.
Information theory (IT) offers a rigorous mathematical framework to formalize, understand, and effectively control that information flow. IT allows comparing, directly and quantitatively, distinct computational scenarios, incorporating assumptions and constraints of the particular models in an explicit fashion, and expressing limits and costs of processing a given task.
Despite those considerable advantages, limitations of IT usage do exist. For instance, the fact that it is computationally very demanding prevents its application to problems with a large dimensionality or scarce data, and plausible biological mechanisms underlying its implementation in vivo remain unclear.
This Special Issue aims to collect contributions that challenge those limitations by proposing new models of cognitive agents in which perception, information processing, learning, and action—in their separated or procedurally connected nature—are addressed using one among the differing IT declinations: Shannon's communication theory, control theory, statistical physics, probabilistic inference, and algorithmic complexity.
Submitted proposals may refer to cognitive agents as computational emulations of specific skills, such as intelligence, engineered to solve complex problems in specific domains, or as frameworks designed to illustrate conjectures and hypotheses about specific aspects of cognition.
Dr. Domenico Maisto
Prof. Dr. Daniel Polani
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- information bottleneck
- empowerment
- free energy principle
- universal artificial intelligence
- minimum description length principle
- Fisher information
