Feeds:
Posts
Comments

Posts Tagged ‘explanation’

  SECOND CALL FOR PAPERS                

for the 7th International and ECAI 2012 Workshop on

EXPLANATION-AWARE COMPUTING (ExaCt 2012)

One-Day Workshop, 27 or 28 August 2012, Montpellier, France
http://exact2012.workshop.hm

** Submission deadline: May 28, 2012 **

When knowledge-based systems are partners in interactive socio-
technical processes, with incomplete and changing problem descriptions,
effective communication between human and software system is vital.
Explanations exchanged between human agents and software agents may
play a key role in such mixed-initiative problem solving. For
example, explanations may increase the confidence of the user in
specific results or in the system as a whole, by providing evidence of
how the results were derived. AI research has also focused on
how computer systems can themselves use explanations, for example to
guide learning. (more…)

Read Full Post »

Do PIPA and SOPA threaten to reverse legal burden of proof in the US?  Clay Shirky argues they do.  I don’t know enough about the legal system, or the proposed legislation.  However, this is a serious allegation with implications far beyond the US.

Read Full Post »

Some readers of RAIL may already with John Bohannon’s brilliant competition Dance your PhD.  In the video below, given at a TED event in Brussels, Bohannon generalizes the point that Dance your PhD essentially makes: Explanations can be effectively delivered in any number of ways.  Though the suggestion that dancers might replace the ubiquitous and dreaded PowerPoint is a bit tongue-in-cheek to be sure, I think that the observations Bohannon makes here about it’s pitfalls are spot on and worthy of consideration.

I have to admit that I’m also seized with curiosity as to how or even whether this could be done with arguments.  At the very least the results would put a whole new “spin” on Michael Gilbert‘s theory of visceral argument. 🙂

Enjoy.

Read Full Post »

Harman announced on Twitter today that the full text of his 1987 book on reasoning, Change in View had been made available for free download at his website.  Readers of RAIL will, I think, find Harman’s book interesting if they’ve not yet been exposed to it.  Chapter 2 in particular will be of interest to many, as Harman there argues that “logic is not of any special relevance” to the theory of reasoning.  Chapter 7, on explanatory coherence is also likely to arouse the interest of many readers. Apart from Chapters two and seven there are treatments of belief revision, implicit commitments, and reason and obligation that are likely to be of interest as well. Harman’s characteristically thorough and challenging analysis are evident throughout Change in View. The book can be downloaded in sections or as one file. Either way, it’s a great opportunity to get a hold of a fascinating book by one of the most influential American philosophers of the last 40 years.

Read Full Post »

Call for Papers

for the 5th International and

ECAI Workshop 2010 on

Explanation-aware Computing

ExaCt 2010

16-17 August, 2010, Lisbon, Portugal

Conference website: http://exact2010.workshop.hm/

Both within AI systems and in interactive systems, the ability to explain reasoning processes and results can substantially affect system usability. For example, in recommender systems good explanations may help to inspire user trust and loyalty, increase satisfaction, make it quicker and easier for users to find what they want, and persuade them to try or buy a recommended item.

Current interest in mixed-initiative systems provides a new context in which explanation issues may play a crucial role. When knowledge-based systems are partners in an interactive socio-technical process, with incomplete and changing problem descriptions, communication between human and software systems is a central part. Explanations exchanged between human agents and software agents may play an important role in mixed-initiative problem solving.

Other disciplines such as cognitive science, linguistics, philosophy of science, psychology, and education have investigated explanation as well. They consider varying aspects, making it clear that there are many different views of the nature of explanation and facets of explanation to explore. Within the field of knowledge-based systems, explanations have been considered as an important link between humans and machines. There, their main purpose has been to increase the confidence of the user in the system’s result, by providing evidence of how it was derived. Additional AI research has focused on how computer systems can themselves use explanations, for example to guide learning.

(more…)

Read Full Post »