Model selection strategies for machine learning algorithms typically involve the numerical optimisation of an appropriate model selection criterion, often based on an estimator of...
In STOC 93, Jones sketched the existence of a hierarchy within problems decidable in linear time by a first-order functional language based on tree-structured data (F), as well a...
We present a discriminative structureprediction model for the letter-to-phoneme task, a crucial step in text-to-speech processing. Our method encompasses three tasks that have bee...
Sittichai Jiampojamarn, Colin Cherry, Grzegorz Kon...
A blind classification algorithm is presented that uses hyperdimensional geometric algorithms to locate a hypothesis, in the form of a convex polytope or hyper-sphere. The convex ...
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...