by Katharina Dost | Apr 29, 2021 | AI Reading Group, News
The key idea behind active learning is that a machine learning algorithm can achieve greater accuracy with fewer training labels if it is allowed to choose the data from which it learns. An active learner may pose queries, usually in the form of unlabeled data...
by Katharina Dost | Apr 16, 2021 | AI Reading Group, News
New methods for time-to-event prediction are proposed by extending the Cox proportional hazards model with neural networks. Building on methodology from nested case-control studies, we propose a loss function that scales well to large data sets, and enables fitting of...
by jkim072 | Apr 12, 2021 | Adversarial Learning, AI Reading Group, Computational Sustainability, News
For many real-world tasks obtaining a complete feature set is prohibitively expensive, especially in healthcare. Specifically, physicians must constantly balance the trade-off between predictive performance and cost for which features to observe. In this paper we...
by Katharina Dost | Feb 18, 2021 | AI Reading Group, News
While methods for comparing two learning algorithms on a single data set have been scrutinized for quite some time already, the issue of statistical tests for comparisons of more algorithms on multiple data sets, which is even more essential to typical machine...
by Katharina Dost | Feb 2, 2021 | AI Reading Group, News
Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics system, learning molecular fingerprints, predicting protein interface, and classifying diseases require a model to learn from graph inputs....
