Global Positioning System (GPS) satellites have a wartime secret: they can suddenly boost their signal power to punch through ...

Abstract: Stochastic gradient descent and other adaptive optimization methods have been proved effective for training deep neural networks. Within each epoch of these methods, the whole training set ...

Agents that operate autonomously benefit from lifelong learning capabilities. However, compatible training algorithms must comply with the decentralized nature of these systems which imposes ...

Abstract: Fast and accurate fault detection and isolation (FDI) for multiple faults is crucial for satellite navigation systems. However, conventional deletion-based greedy search methods suffer from ...

This project aims to reproduce the results of the paper titled "Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints," published in ICML, 2022. The main goal of the ...

Making optimal decisions in the face of noise requires balancing short-term speed and accuracy. But a theory of optimality should account for the fact that short-term speed can influence long-term ...

Federated Learning is a distributed machine learning framework that aims to train a global shared model while keeping their data locally, and previous researches have empirically proven the ideal ...

Recently, there have been many advances in autonomous driving society, attracting a lot of attention from academia and industry. However, existing studies mainly focus on cars, extra development is ...

In patients undergoing mechanical thrombectomy (MT), adjunctive antithrombotic might improve angiographic reperfusion, reduce the risk of distal emboli and reocclusion but possibly expose patients to ...