Learning with prior information
Learning with prior information
A new notion of learnability with prior information is studied: Instead of considering each target function separately, a probability measure on the set of target functions is introduced, quantifying the relative importance assigned to different targets. A necessary and sufficient condition for learnability with prior information of concept classes is given.
- Centre for Artificial Intelligence and Robotics India
- Tata Consultancy Services (India) India
- Brescia University United States
- University of Brescia Italy
learnability, Identification in stochastic control theory, dispersability, Learning and adaptive systems in artificial intelligence, Computational learning theory, Stochastic learning and adaptive control, system identification, prior information
learnability, Identification in stochastic control theory, dispersability, Learning and adaptive systems in artificial intelligence, Computational learning theory, Stochastic learning and adaptive control, system identification, prior information
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).11 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Top 10% impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!