We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
Sanjoy Dasgupta, Adam Tauman Kalai, Claire Montele...
Abstract. We present a formal system that models programmable abstractions for access control. Composite abstractions and patterns of arbitrary complexity are modeled as a configu...
For obtaining a zero defect level, a high fault coverage with respect to the stuck-at fault model is often not sufficient as there are many defects that show a more complex behavi...
We analyze the amount of information needed to carry out model-based recognition tasks, in the context of a probabilistic data collection model, and independently of the recogniti...
We present a set of models for simulating vegetation dynamics in disturbance-prone ecosystems with different complexity levels, integrated in a modelling environment for generatin...