Sciweavers

10054 search results - page 162 / 2011
» On the Complexity of Function Learning
Sort
View
93
Voted
JMLR
2010
82views more  JMLR 2010»
14 years 7 months ago
Negative Results for Active Learning with Convex Losses
We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no b...
Steve Hanneke, Liu Yang
89
Voted
ICALT
2007
IEEE
15 years 7 months ago
Visualizing Narrative Structures and Learning Style Information in Personalized e-Learning Systems
This paper proposes a novel approach to the visualization of complex, but interrelated, sets of information to ease user cognition. Principally, it explores the potential of provi...
Fionán Peter Williams, Owen Conlan
107
Voted
SEMCO
2007
IEEE
15 years 7 months ago
Modeling Discriminative Global Inference
Many recent advances in complex domains such as Natural Language Processing (NLP) have taken a discriminative approach in conjunction with the global application of structural and...
Nicholas Rizzolo, Dan Roth
99
Voted
TEC
2008
98views more  TEC 2008»
15 years 17 days ago
Opposition-Based Differential Evolution
Evolutionary Algorithms (EAs) are well-known optimization approaches to cope with non-linear, complex problems. These population-based algorithms, however, suffer from a general we...
Shahryar Rahnamayan, Hamid R. Tizhoosh, Magdy M. A...
TNN
2008
143views more  TNN 2008»
15 years 17 days ago
Blur Identification by Multilayer Neural Network Based on Multivalued Neurons
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of spe...
Igor N. Aizenberg, Dmitriy Paliy, Jacek M. Zurada,...