Sciweavers

986 search results - page 1 / 198
» Zero-data Learning of New Tasks
Sort
View
AAAI
2008
15 years 11 hour ago
Zero-data Learning of New Tasks
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
Hugo Larochelle, Dumitru Erhan, Yoshua Bengio
CSCW
2008
ACM
14 years 9 months ago
Unpacking Tasks: The Fusion of New Technology with Instructional Work
This paper discusses how a new technology (designed to help pupils with learning about Shakespeare's Macbeth) is introduced and integrated into existing classroom practices. I...
Christian Greiffenhagen
IS
2010
14 years 8 months ago
Identifying user strategies in exploratory learning with evolving task modelling
Abstract—In this paper we present work on adaptive identification of learners’ strategies, gradually developing a higher level of adaptation based on evolving models of mathem...
Mihaela Cocea, George D. Magoulas
ICMLA
2003
14 years 11 months ago
Reinforcement Learning Task Clustering
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
James L. Carroll, Todd S. Peterson, Kevin D. Seppi
ICML
1996
IEEE
15 years 1 months ago
Discovering Structure in Multiple Learning Tasks: The TC Algorithm
Recently, there has been an increased interest in "lifelong" machine learning methods, that transfer knowledge across multiple learning tasks. Such methods have repeated...
Sebastian Thrun, Joseph O'Sullivan