I
Idan Achituve
Researcher at Bar-Ilan University
Publications - 14
Citations - 189
Idan Achituve is an academic researcher from Bar-Ilan University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 3, co-authored 8 publications receiving 50 citations.
Papers
More filters
Posted Content
Self-Supervised Learning for Domain Adaptation on Point-Clouds
TL;DR: A new family of pretext tasks, Deformation Reconstruction, inspired by the deformations encountered in sim-to-real transformations are introduced, and a novel training procedure for labeled point cloud data motivated by the MixUp method called Point cloud Mixup (PCM).
Proceedings ArticleDOI
Self-Supervised Learning for Domain Adaptation on Point Clouds
TL;DR: In this article, a new family of pretext tasks, Deformation Reconstruction, inspired by the deformations encountered in sim-to-real transformations, is introduced for domain adaptation on point clouds.
Posted Content
Auxiliary Learning by Implicit Differentiation
TL;DR: A novel framework, AuxiLearn, is proposed that targets both challenges of designing useful auxiliary tasks and combining auxiliary tasks into a single coherent loss, based on implicit differentiation.
Proceedings Article
Multi-Task Learning as a Bargaining Game
TL;DR: A new MTL optimization procedure, Nash-MTL, is described, which achieves state-of-the-art results on multiple MTL benchmarks in various domains and derives theoretical guarantees for its convergence.
Proceedings ArticleDOI
Interpretable Online Banking Fraud Detection Based On Hierarchical Attention Mechanism
TL;DR: This work proposes an attention based architecture for classifying online banking transactions as either fraudulent or genuine, and allows transparency to its decision by identifying the most important transactions in the sequence and the most informative features in each transaction.