Sciweavers

7378 search results - page 395 / 1476
» Introduction to Machine Learning
Sort
View
ICML
2004
IEEE
16 years 7 months ago
Apprenticeship learning via inverse reinforcement learning
We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we wa...
Pieter Abbeel, Andrew Y. Ng
ICML
2002
IEEE
16 years 7 months ago
Active + Semi-supervised Learning = Robust Multi-View Learning
In a multi-view problem, the features of the domain can be partitioned into disjoint subsets (views) that are sufficient to learn the target concept. Semi-supervised, multi-view a...
Ion Muslea, Steven Minton, Craig A. Knoblock
ICALT
2008
IEEE
16 years 1 months ago
Interaction Analysis as a Multi-Support Approach of Social Computing for Learning, in the "Collaborative Era": Lessons Learned b
Apparently computer technology is shifting its focus, with individual users not being the main target any more. The evolution of Web 2.0 technologies is promoting the development ...
Tharrenos Bratitsis, Angelique Dimitracopoulou
ECTEL
2010
Springer
15 years 8 months ago
Deep Learning Design for Sustainable Innovation within Shifting Learning Landscapes
Changes in the underpinning technologies for TEL is occurring at a pace that we have never before experienced, and this is unlikely to slow down. This necessitates a broader and mo...
Andrew Ravenscroft, Tom Boyle, John Cook, Andreas ...
ICML
2005
IEEE
16 years 7 months ago
Exploration and apprenticeship learning in reinforcement learning
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
Pieter Abbeel, Andrew Y. Ng