Sciweavers

1800 search results - page 160 / 360
» Learning Restart Strategies
Sort
View
PAMI
2011
14 years 12 months ago
Semi-Supervised Learning via Regularized Boosting Working on Multiple Semi-Supervised Assumptions
—Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learni...
Ke Chen, Shihai Wang
HICSS
2009
IEEE
147views Biometrics» more  HICSS 2009»
15 years 11 months ago
Determining a Firm's Optimal Outsourcing Rate: A Learning Model Perspective
We present a decision model of a firm’s optimal outsourcing rate as an extension of Cha et. al [1]’s previous work on the economic risk of knowledge loss and deskilling in the...
Hoon S. Cha, David E. Pingry, Matt E. Thatcher
ISDA
2009
IEEE
15 years 11 months ago
Postponed Updates for Temporal-Difference Reinforcement Learning
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Harm van Seijen, Shimon Whiteson
CP
2004
Springer
15 years 10 months ago
Decomposition and Learning for a Hard Real Time Task Allocation Problem
Abstract. We present a cooperation technique using an accurate management of nogoods to solve a hard real-time problem which consists in assigning periodic tasks to processors in t...
Hadrien Cambazard, Pierre-Emmanuel Hladik, Anne-Ma...
123
Voted
EDM
2010
101views Data Mining» more  EDM 2010»
15 years 6 months ago
Off Topic Conversation in Expert Tutoring: Waste of Time or Learning Opportunity
While many aspects of tutoring have been identified and studied, off topic conversation has been largely ignored. In this paper, off topic conversation during 50 hours of one-to-on...
Blair Lehman, Whitney L. Cade, Andrew Olney