This paper introduces a new approach for machine teaching that
partly addresses the (unavoidable) mismatch between what the
teacher assumes about the learning process of the student and the
actual process. We analyze several situations in which such mismatch
takes place, including when the student?s learning algorithm
is known but the corresponding parameters are not, and when the
learning algorithm itself is not known. Our analysis is focused on
the case of a Bayesian Gaussian learner, and we show that, even
in this simple case, the lack of knowledge regarding the student?s
learning process significantly deteriorates the performance of machine
teaching: while perfect knowledge of the student ensures that
the target is learned after a finite number of samples, lack of knowledge
thereof implies that the student will only learn asymptotically
(i.e., after an infinite number of samples). We introduce interactivity
as a means to mitigate the impact of imperfect knowledge
and show that, by using interactivity, we are able to recover finite
learning time, in the best case, or significantly faster convergence,
in the worst case. Finally, we discuss the extension of our analysis
to a classification problem using linear discriminant analysis, and
discuss the implications of our results in single- and multi-student
settings.
Articles you may be interested inMicellar interactions in water-AOT based droplet microemulsions containing hydrophilic and amphiphilic polymers Monte Carlo cluster algorithm for fluid phase transitions in highly size-asymmetrical binary mixtures Phase behavior and structure of star-polymer-colloid mixtures A continuum microscopic model for symmetric amphiphilic mixtures, is generalized by considering explicitly water-oil asymmetry, through the interactions between amphiphiles and water and oil. The phase diagram, including lamellar phases, and the properties of water-oil interfaces are studied, using an approximate free energy density-functional, for a wide range of amphiphilic interactions. We also consider the structure and stability of spherical micelles and study the dilute micellar regime. By combining the microscopic density-functional description with the phenomenologic Helfrich elastic free energy, we calculate the elastic properties of the amphiphilic film. Our results for the elastic constant, k s ϭ2kϩk , are compared with experimental data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.