Sciweavers

532 search results - page 19 / 107
» Toward interactive training and evaluation
Sort
View
NAACL
2010
13 years 7 months ago
Engaging learning groups using Social Interaction Strategies
Conversational Agents have been shown to be effective tutors in a wide range of educational domains. However, these agents are often ignored and abused in collaborative learning s...
Rohit Kumar, Carolyn Penstein Rosé
NN
1998
Springer
156views Neural Networks» more  NN 1998»
13 years 9 months ago
Automatic early stopping using cross validation: quantifying the criteria
Cross validation can be used to detect when over tting starts during supervised training of a neural network; training is then stopped before convergence to avoid the overtting  ...
Lutz Prechelt
NORDICHI
2004
ACM
14 years 3 months ago
Marrying HCI/Usability and computer games: a preliminary look
The fields HCI/usability and computer games have existed for a few decades with virtually no mutual interaction. However, in recent years, a number of exchanges have appeared, bot...
Anker Helms Jørgensen
KCAP
2009
ACM
14 years 4 months ago
Interactively shaping agents via human reinforcement: the TAMER framework
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without n...
W. Bradley Knox, Peter Stone
CHI
2003
ACM
14 years 10 months ago
Recommending collaboration with social networks: a comparative evaluation
Studies of information seeking and workplace collaboration often find that social relationships are a strong factor in determining who collaborates with whom. Social networks prov...
David W. McDonald