T
Tassilo Klein
Researcher at University of Trento
Publications - 59
Citations - 2289
Tassilo Klein is an academic researcher from University of Trento. The author has contributed to research in topics: Deep learning & Commonsense reasoning. The author has an hindex of 15, co-authored 56 publications receiving 1532 citations. Previous affiliations of Tassilo Klein include Brigham and Women's Hospital & Technische Universität München.
Papers
More filters
Posted Content
Differentially Private Federated Learning: A Client Level Perspective
TL;DR: The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance, and empirical studies suggest that given a sufficiently large number of participating clients, this procedure can maintain client-level differential privacy at only a minor cost in model performance.
Journal ArticleDOI
DeepNAT: Deep convolutional neural network for segmenting neuroanatomy.
TL;DR: DeepNAT is an end‐to‐end learning‐based approach to brain segmentation that jointly learns an abstract feature representation and a multi‐class classification and the results show that DeepNAT compares favorably to state‐of‐the‐art methods.
Proceedings ArticleDOI
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
TL;DR: Dynamic Generative Memory (DGM) as mentioned in this paper relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking and proposes a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks.
Journal ArticleDOI
Ultrasound confidence maps using random walks.
TL;DR: This work introduces a method for estimating a per-pixel confidence in the information depicted by ultrasound images, referred to as an ultrasound confidence map, which emphasizes uncertainty in attenuated and/or shadow regions, within a random walks framework by taking into account ultrasound specific constraints.
Posted Content
Contrastive Self-Supervised Learning for Commonsense Reasoning
Tassilo Klein,Moin Nabi +1 more
TL;DR: A self-supervised method to solve Pronoun Disambiguation and Winograd Schema Challenge problems is proposed, based on the recently introduced transformer networks, BERT, that exhibits strong performance on many NLP benchmarks.