The rapid increase in medical and biomedical image acquisition rates has opened up new avenues for image analysis, but has also introduced formidable challenges. This is evident, for example, in selective plane illumination microscopy where acquisition rat ...
Institute of Electrical and Electronics Engineers2021
Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression method that gener ...
As power grids transition towards low-inertia net-works based on converter-interfaced renewable energy resources, they become increasingly vulnerable to extreme dynamics. Currently, the most advanced methods for signal processing in power systems are embed ...
This paper introduces a new algorithm for consensus optimization in a multi-agent network, where all agents collaboratively find a minimizer for the sum of their private functions. All decentralized algorithms rely on communications between adjacent nodes. ...
Compressed Sensing teaches us that measurements can be traded for offline computation if the signal being sensed has a simple enough representation. Proper decoders can exactly recover the high-dimensional signal of interest from a lower-dimensional vector ...
Recent advances in signal processing, machine learning and deep learning with sparse intrinsic structure of data have paved the path for solving inverse problems in acoustics and audio. The main task of this thesis was to bridge the gap between the powerfu ...
This thesis focuses on developing efficient algorithmic tools for processing large datasets. In many modern data analysis tasks, the sheer volume of available datasets far outstrips our abilities to process them. This scenario commonly arises in tasks incl ...
In my thesis, I reveal several already-existing and emerging challenges in multi-objective management of multiprocessor systems, and address them through novel solutions, from heuristics to RL, depending on the complexity of the problem. Conventional multi ...
