Sciweavers

540 search results - page 2 / 108
» Graph-based transfer learning
Sort
View
ICML
2007
IEEE
14 years 6 months ago
Cross-domain transfer for reinforcement learning
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
Matthew E. Taylor, Peter Stone
PAMI
2012
11 years 7 months ago
Quantifying and Transferring Contextual Information in Object Detection
— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
Wei-Shi Zheng, Shaogang Gong, Tao Xiang
ECML
2006
Springer
13 years 9 months ago
Graph Based Semi-supervised Learning with Sharper Edges
In many graph-based semi-supervised learning algorithms, edge weights are assumed to be fixed and determined by the data points' (often symmetric) relationships in input space...
Hyunjung Shin, N. Jeremy Hill, Gunnar Rätsch
IJCAI
2007
13 years 6 months ago
Graph-Based Semi-Supervised Learning as a Generative Model
This paper proposes and develops a new graph-based semi-supervised learning method. Different from previous graph-based methods that are based on discriminative models, our method...
Jingrui He, Jaime G. Carbonell, Yan Liu 0002
DAWAK
2005
Springer
13 years 10 months ago
Graph-Based Modeling of ETL Activities with Multi-level Transformations and Updates
Extract-Transform-Load (ETL) workflows are data centric workflows responsible for transferring, cleaning, and loading data from their respective sources to the warehouse. Previous ...
Alkis Simitsis, Panos Vassiliadis, Manolis Terrovi...