Fully automatic deep learning has become the state-of-the-art technique for many tasks
including image acquisition, analysis and interpretation, and for the extraction of clinically …

Learning curves provide insight into the dependence of a learner's generalization
performance on the training set size. This important tool can be used for model selection, to …

We present a holistic approach to building a robust and useful natural language
classification system for real-world content moderation. The success of such a system relies …

The performance of deep neural networks improves with more annotated data. The problem
is that the budget for annotation is limited. One solution to this is active learning, where a …

Data collection is a major bottleneck in machine learning and an active research topic in
multiple communities. There are largely two reasons data collection has recently become a …

Abstract Machine Learning (ML) models are increasingly deployed in the wild to perform a
wide range of tasks. In this work, we ask to what extent can an adversary steal functionality …

Semi-supervised learning has greatly advanced medical image segmentation since it
effectively alleviates the need of acquiring abundant annotations from experts, wherein the …

Various strategies for active learning have been proposed in the machine learning literature.
In uncertainty sampling, which is among the most popular approaches, the active learner …

In this work, we provide a survey of active learning (AL) for its applications in natural
language processing (NLP). In addition to a fine-grained categorization of query strategies …

Generally, data is available abundantly in unlabeled form, and its annotation requires some
cost. The labeling, as well as learning cost, can be minimized by learning with the minimum …