Sciweavers

265 search results - page 8 / 53
» Context in Artificial Intelligence: I. A Survey of the Liter...
Sort
View
CHI
2011
ACM
12 years 11 months ago
Should I open this email?: inbox-level cues, curiosity and attention to email
The quantity of email people receive each day can be overwhelming. Previous research suggests that when handling email, individuals prioritize certain messages for attention over ...
Jaclyn Wainer, Laura Dabbish, Robert Kraut
ATAL
2010
Springer
13 years 8 months ago
Learning context conditions for BDI plan selection
An important drawback to the popular Belief, Desire, and Intentions (BDI) paradigm is that such systems include no element of learning from experience. In particular, the so-calle...
Dhirendra Singh, Sebastian Sardiña, Lin Pad...
IWC
2008
99views more  IWC 2008»
13 years 7 months ago
Pedagogy and usability in interactive algorithm visualizations: Designing and evaluating CIspace
Interactive algorithm visualizations (AVs) are powerful tools for teaching and learning concepts that are difficult to describe with static media alone. However, while countless A...
Saleema Amershi, Giuseppe Carenini, Cristina Conat...
FLAIRS
2004
13 years 8 months ago
Being as Informative as the User Wants: The Generation of Information Enriched Utterances
The work in this paper is based on the claim that collaborative dialogue involves taking into account how much information an utterance conveys, in the sense that it thereby shows...
Stina Ericsson
GECCO
2005
Springer
136views Optimization» more  GECCO 2005»
14 years 27 days ago
Preventing overfitting in GP with canary functions
Overfitting is a fundamental problem of most machine learning techniques, including genetic programming (GP). Canary functions have been introduced in the literature as a concept ...
Nate Foreman, Matthew P. Evett