Motivated by the recent successes of neural networks that have the ability to fit the data perfectlyand generalize well, we study the noiseless model in the fundamental least-squares setup.

Unfortunately,optimizing anetworkusingthe desired evaluation metric, such asF1-Score, istypically not feasible.

In this paper, we initiate the study of Euclidean clustering with Distance-based privacy. Distance-based privacy is motivated by the fact that it is often only needed to protect the privacy of exact, rather than approximate, locations.

To unveil how the brain learns, ongoing work seeks biologically-plausible approximations of gradient descent algorithms for training recurrent neural networks (RNNs).