Sciweavers

43 search results - page 5 / 9
» Hardness of Learning Halfspaces with Noise
Sort
View
ALT
2006
Springer
15 years 8 months ago
Active Learning in the Non-realizable Case
Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly c...
Matti Kääriäinen
90
Voted
ALT
2001
Springer
15 years 4 months ago
Learning Coherent Concepts
We develop a theory for learning scenarios where multiple learners co-exist but there are mutual compatibility constraints on their outcomes. This is natural in cognitive learning...
Ashutosh Garg, Dan Roth
DATE
2010
IEEE
185views Hardware» more  DATE 2010»
15 years 4 months ago
Fault diagnosis of analog circuits based on machine learning
— We discuss a fault diagnosis scheme for analog integrated circuits. Our approach is based on an assemblage of learning machines that are trained beforehand to guide us through ...
Ke Huang, Haralampos-G. D. Stratigopoulos, Salvado...
110
Voted
FOCS
2008
IEEE
15 years 6 months ago
What Can We Learn Privately?
Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept ...
Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi ...
KDD
2012
ACM
207views Data Mining» more  KDD 2012»
13 years 2 months ago
Robust multi-task feature learning
Multi-task learning (MTL) aims to improve the performance of multiple related tasks by exploiting the intrinsic relationships among them. Recently, multi-task feature learning alg...
Pinghua Gong, Jieping Ye, Changshui Zhang