Sciweavers

2960 search results - page 70 / 592
» Learning from Multiple Sources
Sort
View
CVPR
2010
IEEE
15 years 6 months ago
Learning from Interpolated Images using Neural Networks for Digital Forensics
Interpolated images have data redundancy, and special correlation exists among neighboring pixels, which is a crucial clue in digital forensics. We design a neural network based f...
Yizhen Huang, Na Fan
ATAL
2008
Springer
14 years 12 months ago
Graph Laplacian based transfer learning in reinforcement learning
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transfer...
Yi-Ting Tsao, Ke-Ting Xiao, Von-Wun Soo
AIED
2009
Springer
15 years 4 months ago
Intelligent Tutoring Systems with Multiple Representations and Self-Explanation Prompts Support Learning of Fractions
Although a solid understanding of fractions is foundational in mathematics, the concept of fractions remains a challenging one. Previous research suggests that multiple graphical r...
Martina A. Rau, Vincent Aleven, Nikol Rummel
ITA
2007
101views Communications» more  ITA 2007»
14 years 9 months ago
Learning tree languages from text
We study the problem of learning regular tree languages from text. We show that the framework of function distinguishability as introduced by the author in Theoretical Computer Sc...
Henning Fernau
APLAS
2010
ACM
14 years 10 months ago
Automatically Inferring Quantified Loop Invariants by Algorithmic Learning from Simple Templates
Abstract. By combining algorithmic learning, decision procedures, predicate abstraction, and simple templates, we present an automated technique for finding quantified loop invaria...
Soonho Kong, Yungbum Jung, Cristina David, Bow-Yaw...