In recent years, large scale land cover maps constructed from remotely sensed data have become important information sources for resource management. Classifiers are commonly used to predict land cover for unsampled map units; hence, they play a key role in map construction. Achieving adequate classifier accuracy is often problematic for highly variable and difficult-to-sample landscapes. This ...

We develop a general framework for margin-based multicategory classification in metric spaces. The basic work-horse is a margin-regularized version of the nearest-neighbor classifier. We prove generalization bounds that match the state of the art in sample size n and significantly improve the dependence on the number of classes k. Our point of departure is a nearly Bayes-optimal finite-sample r...

We investigate spin correlations in the dipolar Heisenberg antiferromagnet Gd2Sn2O7 using polarised neutron-scattering measurements in the correlated paramagnetic regime. Using Monte Carlo methods, we show that our data are sensitive to weak further-neighbour exchange interactions of magnitude  ∼0.5% of the nearest-neighbour interaction, and are compatible with either antiferromagnetic next-nea...

The scattering number is a measure of the vulnerability of a graph. In this paper we investigate a refinement that involves the neighbour isolated version of the parameter. The neighbour isolated scattering number of a noncomplete graph G is defined to be NIS(G) =max{i(G/X )−|X | : i(G/X )3⁄4 1} where the maximum is taken over all X , the cut strategy of G, and i(G/X ) is the number of componen...

The Neighbour Search (NS) algorithm, is an iterative method for constructing Pareto sets of multi-dimensional polytopes. A NS iteration consists in two steps: Edges Exploration and Neighbour Detection. Edges Exploration takes a Pareto vertex and determines all Pareto edges connecting such a Pareto vertex to its neighbours. Each neighbour is again a Pareto vertex that is obtained by Neighbour De...

(1) Competitive ability can be compared between species in two ways: effect of different neighbour species on performance of a single target species or response of different arget species to a single neighbour species. In a 5-week glasshouse experiment, an additive design was used for all combinations of seven species as both target and neighbour species to determine if there were consistent hi...