Sciweavers

779 search results - page 62 / 156
» Reinforcement Using Supervised Learning for Policy Generaliz...
Sort
View
IJCAI
2007
13 years 9 months ago
Effective Control Knowledge Transfer through Learning Skill and Representation Hierarchies
Learning capabilities of computer systems still lag far behind biological systems. One of the reasons can be seen in the inefficient re-use of control knowledge acquired over the...
Mehran Asadi, Manfred Huber
EMNLP
2008
13 years 9 months ago
Soft-Supervised Learning for Text Classification
We propose a new graph-based semisupervised learning (SSL) algorithm and demonstrate its application to document categorization. Each document is represented by a vertex within a ...
Amarnag Subramanya, Jeff Bilmes
SMC
2007
IEEE
102views Control Systems» more  SMC 2007»
14 years 2 months ago
An improved immune Q-learning algorithm
—Reinforcement learning is a framework in which an agent can learn behavior without knowledge on a task or an environment by exploration and exploitation. Striking a balance betw...
Zhengqiao Ji, Q. M. Jonathan Wu, Maher A. Sid-Ahme...
ACL
2009
13 years 5 months ago
A Graph-based Semi-Supervised Learning for Question-Answering
We present a graph-based semi-supervised learning for the question-answering (QA) task for ranking candidate sentences. Using textual entailment analysis, we obtain entailment sco...
Asli Çelikyilmaz, Marcus Thint, Zhiheng Hua...
ICDM
2008
IEEE
112views Data Mining» more  ICDM 2008»
14 years 2 months ago
Supervised Inductive Learning with Lotka-Volterra Derived Models
We present a classification algorithm built on our adaptation of the Generalized Lotka-Volterra model, well-known in mathematical ecology. The training algorithm itself consists ...
Karen Hovsepian, Peter Anselmo, Subhasish Mazumdar