587 citations
- Delft University of TechnologyNL6 papers
- ETH ZurichCH4 papers
- University of BaselCH4 papers
- Beijing Institute of TechnologyCN2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Ericsson (Sweden)SE2 papers
- Forschungszentrum JülichDE2 papers
- KTH Royal Institute of TechnologySE2 papers
- Aalto UniversityFI1 paper
- ABB (Canada)CA1 paper
- ABB (India)IN1 paper
- Association for Computing MachineryUS1 paper
6 papers · 1 filter
PipeTune: Pipeline Parallelism of Hyper and System Parameters Tuning for Deep Learning Clusters
Isabelly Rocha, Nathaniel Morris, Lydia Y. Chen +3
DNN learning jobs are common in today's clusters due to the advances in AI driven services such as machine translation and image recognition. The most critical phase of these jobs…
ExpertNet: Adversarial Learning and Recovery Against Noisy Labels
Amirmasoud Ghiassi, Robert Birke, Rui Han +1
Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant por…
Advances in Asynchronous Parallel and Distributed Optimization
Mahmoud Assran, Arda Aytekin, Hamid Feyzmahdavian +2
Motivated by large-scale optimization problems arising in the context of machine learning, there have been several advances in the study of asynchronous parallel and distributed op…
Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
Martin Kotuliak, Sandro E. Schoenborn, Andrei Dan
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work int…
The Separator, a Two-Phase Oil and Water Gravity CPS Separator Testbed
Michael Breza, Laksh Bhatia, Ivana Tomic +4
Industrial Control Systems (ICS) are evolving with advances in new technology. The addition of wireless sensors and actuators and new control techniques means that engineering prac…
QActor: On-line Active Learning for Noisy Labeled Stream Data
Taraneh Younesian, Zilong Zhao, Amirmasoud Ghiassi +2
Noisy labeled data is more a norm than a rarity for self-generated content that is continuously published on the web and social media. Due to privacy concerns and governmental regu…