Special Issue "Probabilistic Causal Modelling in Intelligent Systems"

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 1 August 2018

Special Issue Editors

Guest Editor
Dr. Kevin B Korb

Faculty of Information Technology´╝îMonash University, Clayton, Victoria 3800, Australia
Website | E-Mail
Interests: causal models; causal discovery; Bayesian networks
Guest Editor
Prof. Ann E Nicholson

Clayton School of Information Technology, Monash University, Clayton, Victoria 3800, Australia
Website | E-Mail
Interests: artificial intelligence; Bayesian networks; data mining; evolutionary ethics; intelligent agents; knowledge engineering; plan recognition; probabilistic reasoning; user modelling
Guest Editor
Mr. Erik Nyberg

Clayton School of Information Technology, Monash University, Clayton, Victoria 3800, Australia
Website | E-Mail
Interests: artificial intelligence; Bayesian networks

Special Issue Information

Dear Colleagues,

Probabilistic Causality—the idea that causality is stochastic and that probabilistic dependencies reveal their causal foundations—has come a long way since its origins with the work of Hans Reichenbach in the 1950s. After losing its reductionist pretensions in the 1970s and 1980s in debates within Philosophy of Science, it crashed headlong into the Bayesian network technology emerging from Statistics and Artificial Intelligence (AI). Out of that collision, in the late 1980s, grew some remarkable innovations, including the Causal Discovery programs of Clark Glymour and collaborators in Philosophy and Judea Pearl and others in AI. The technology and new ideas have continued to flow, and at a great pace. This Special Issue on “Probabilistic Causal Modelling” will provide a view of where we have come from, a snapshot of where we are, and a probabilistic prediction of where we are headed.

Dr. Kevin B Korb
Prof. Ann E Nicholson
Mr. Erik Nyberg
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 papers will be 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. Information 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 850 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

  • causal Bayesian networks
  • probabilistic graphical models
  • probabilistic causality
  • information theory
  • causal power

Published Papers

This special issue is now open for submission, see below for planned papers.

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Probabilistic Actual Causation
Author: Luke Fenton-Glynn
Affiliation: Department of Philosophy, University College London, Gower Street, London, WC1E 6BT, UK
Abstract: Actual (token) causes – e.g. Suzy’s being exposed to asbestos –often bring about their effects – e.g. Suzy’s suffering mesothelioma – probabilistically. I use probabilistic causal models to tackle one of the thornier difficulties for traditional accounts of probabilistic actual causation: namely probabilistic preemption.

 

Title: The Red Herring of Probability Raising
Author: Naftali Weinberger
Email: naftali.weinberger@gmail.com
Abstract: Theorists of probabilistic causality analyzed causation as probability raising relative to particular contexts. In contrast, more recent graphical theories are less concerned with whether a cause raises or lowers the probability of an effect, but, more generally, with whether it changes the probability of its effect. While this difference between the accounts may seem minor, here I argue that the focus on probability raising hindered theorists of probabilistic causality from grasping the relationship between causation and probability. The idea that causation is linked to a specific quantitative probabilistic relationship led these theorists to conflate issues about confounding with those related to effect heterogeneity, and to engage in debates that in retrospect do not appear to reflect substantive philosophical differences. In contrast, graphical causal models only rely on qualitative assumptions, and relegate the inference of the quantitative relationship between an effect and its causes to statistical methods. This contrast is key to understanding the philosophical differences between probabilistic and graphical accounts of causation. 

 

 

Back to Top