The ML type system was originally introduced as a means of identifying a class of terms in a simple untyped language, often referred to as core-ML, whose evaluation could be guaran...
Binary decision trees based on univariate splits have traditionally employed so-called impurity functions as a means of searching for the best node splits. Such functions use estim...
Object search in a visual scene is a highly challenging and computationally intensive task. Most of the current object detection techniques extract features from images for classi...
We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
In this work the authors present an analytical model that -- compared to previously published work -- more accurately captures the delay of IEEE 802.11 protocol under low, medium,...