Sciweavers

3084 search results - page 175 / 617
» Learning to Take Actions
Sort
View
84
Voted
IJCAI
2003
14 years 11 months ago
Approximate Policy Iteration using Large-Margin Classifiers
We present an approximate policy iteration algorithm that uses rollouts to estimate the value of each action under a given policy in a subset of states and a classifier to general...
Michail G. Lagoudakis, Ronald Parr
80
Voted
IJON
2002
130views more  IJON 2002»
14 years 10 months ago
Error-backpropagation in temporally encoded networks of spiking neurons
For a network of spiking neurons that encodes information in the timing of individual spike times, we derive a supervised learning rule, SpikeProp, akin to traditional errorbackpr...
Sander M. Bohte, Joost N. Kok, Johannes A. La Pout...
CHI
1998
ACM
15 years 2 months ago
When the Interface is a Talking Dinosaur: Learning Across Media with ActiMates Barney
ActiMates™ Barney™ represents a new form of interactive learning product for two- to five-year old children: a small computer that looks like an animated plush doll. He can be...
Erik Strommen
77
Voted
IJAR
2006
118views more  IJAR 2006»
14 years 10 months ago
Learning Bayesian network parameters under order constraints
We consider the problem of learning the parameters of a Bayesian network from data, while taking into account prior knowledge about the signs of influences between variables. Such...
A. J. Feelders, Linda C. van der Gaag
65
Voted
CAI
2004
Springer
14 years 10 months ago
On the Use of the Choquet Integral for the Collaborative Creation of Learning Objects
Abstract. Computer-supported collaborative knowledge creation is the continuous process of development of knowledge assets, where produced knowledge has to be assessed by the devel...
Juan Manuel Dodero, Miguel-Ángel Sicilia, C...