Robust learning with infinite additional information

Robust Learning with Infinite Additional Information

The present work investigates Gold style algorithmic learning from input-output examples whereby the learner has access to oracles as additional information. Furthermore this access has to be robust , that means that a single learning algorithm has to succeed with every oracle which meets a given speciication. The rst main result considers oracles of the same Turing degree: Robust learning with...

Robust Regulation of Infinite-Dimensional Systems with Infinite-Dimensional Exosystems

In this paper robust regulation problem for infinite-dimensional systems with infinitedimensional exosystems is discussed. The exosystems considered in this paper have infinite number of eigenvalues on the imaginary axis and thus include periodic signals. It is shown that there exists a feedback controller which robustly regulates the class of signals generated by the exosystem and strongly sta...

Parameter estimation with additional information

Inductive Inference with Additional Information

We consider the problem of inductively inferring a grammar for a language, given (positive) examples of the language and putative (possibly faulty) grammars for the complement of the language. The criterion of success is identification in the limit, defined by E. M. Gold (1967, Inform. and Control 10, 447 474). Additional information is useful insofar as it allows the identification of language...

Video Processing with Additional Information

Title of dissertation: VIDEO PROCESSING WITH ADDITIONAL INFORMATION Mahesh Ramachandran, Doctor of Philosophy, 2010 Dissertation directed by: Professor Rama Chellappa Department of Electrical and Computer Engineering Cameras are frequently deployed along with many additional sensors in aerial and ground-based platforms. Many video datasets have metadata containing measurements from inertial sen...