81 citations · 110 across the 5 of their papers we have counts for
5 papers
Diffusion-based Deep Active Learning
Dan Kushnir, Luca Venturi
The remarkable performance of deep neural networks depends on the availability of massive labeled data. To alleviate the load of data annotation, active deep learning aims to selec…
Active Community Detection with Maximal Expected Model Change
Dan Kushnir, Benjamin Mirabelli
We present a novel active learning algorithm for community detection on networks. Our proposed algorithm uses a Maximal Expected Model Change (MEMC) criterion for querying network…
Linear Time Clustering for High Dimensional Mixtures of Gaussian Clouds
Dan Kushnir, Shirin Jalali, Iraj Saniee
Clustering mixtures of Gaussian distributions is a fundamental and challenging problem that is ubiquitous in various high-dimensional data processing tasks. While state-of-the-art…
Manifold Learning: The Price of Normalization
Y. Goldberg, A. Zakai, D. Kushnir +1
We analyze the performance of a class of manifold-learning algorithms that find their output by minimizing a quadratic form under some normalization constraints. This class consist…
Geometry of intensive scalar dissipation events in turbulence
Dan Kushnir, Joerg Schumacher, Achi Brandt
Maxima of the scalar dissipation rate in turbulence appear in form of sheets and correspond to the potentially most intensive scalar mixing events. Their cross-section extension de…