In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have be...
In this paper we apply the recent notion of anytime universal intelligence tests to the evaluation of a popular reinforcement learning algorithm, Q-learning. We show that a general...
A mechanism for releasing information about a statistical database with sensitive data must resolve a trade-off between utility and privacy. Publishing fully accurate information ...
Arpita Ghosh, Tim Roughgarden, Mukund Sundararajan
This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class mode...
Randomization is vital in cryptography: secret keys should be randomly generated and most cryptographic primitives (e.g., encryption) must be probabilistic. As a bstraction, it is...