activity
20172023
most citedFederated Learning for IoUT: Concepts, Applications, Challenges and Opportunities

12 citations · 22 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2023★ 1 cited

Comparing NARS and Reinforcement Learning: An Analysis of ONA and -Learning Algorithms

Ali Beikmohammadi, Sindri Magnússon

In recent years, reinforcement learning (RL) has emerged as a popular approach for solving sequence-based tasks in machine learning. However, finding suitable alternatives to RL re…

cs.LG2023★ 2 cited

Human-Inspired Framework to Accelerate Reinforcement Learning

Ali Beikmohammadi, Sindri Magnússon

Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions…

cs.LG2022★ 12 cited

Federated Learning for IoUT: Concepts, Applications, Challenges and Opportunities

Nancy Victor, Rajeswari. C, Mamoun Alazab +5

Internet of Underwater Things (IoUT) have gained rapid momentum over the past decade with applications spanning from environmental monitoring and exploration, defence applications,…

cs.LG2022★ 1 cited

Delay-adaptive step-sizes for asynchronous learning

Xuyang Wu, Sindri Magnusson, Hamid Reza Feyzmahdavian +1

In scalable machine learning systems, model training is often parallelized over multiple nodes that run without tight synchronization. Most analysis results for the related asynchr…

cs.LG2020

The Internet of Things as a Deep Neural Network

Rong Du, Sindri Magnússon, Carlo Fischione

An important task in the Internet of Things (IoT) is field monitoring, where multiple IoT nodes take measurements and communicate them to the base station or the cloud for processi…

cs.LG2020

Communication-efficient Variance-reduced Stochastic Gradient Descent

Hossein S. Ghadikolaei, Sindri Magnusson

We consider the problem of communication efficient distributed optimization where multiple nodes exchange important algorithm information in every iteration to solve large problems…