Projects
New-to-nature Biological Sensors: Unlocking the full potential of biological sensors beyond nature Ghent University
“If you can not measure it, you can not improve it” (Lord Kelvin) clearly articulates the need for efficient and robust sensors in all fields of science and technology, especially in pharma, agriculture, environment, food and industrial biotechnology. However, current analytic techniques require laborious, expensive multi-step processes with highly specialized, non-portable equipment. As a solution, all living organisms have been evolving and ...
Low cost bridge health monitoring by ambient vibration tests using wireless sensors (Spanish) Ensayos dinámicos de bajo coste para el mantenimiento de puentes sometidos a cargas ambientales no controladas, utilizando sensores inalámbricos. KU Leuven
Kernels, tensors and structured data. KU Leuven
SPECTRAI - Spectral image Processing with Efficiently Compressed TensoRs and AI KU Leuven
Tensors and Neural Networks for Computational Creativity KU Leuven
Creativity in language is ubiquitous. It is abundantly present in work with an explicit creative intention - such as literary novels or poems - but weighty doses of creativity also pervade everyday language use. We believe that a computational model of creativity that focuses on language will shed light on the enigmatic processes and interactions that come into play when we humans express ourselves in creative ways. Moreover, natural language ...
Tensors and Neural Networks for Creative Language Generation KU Leuven
Machine learning with tensors for hyper spectral imaging for agrofood and medical applications KU Leuven
Study of Canonical Polyadic Decomposition of Higher-Order Tensors KU Leuven
time, frequency,temperature, etc.) and are therefore naturally represented by higher-order arrays of numerical values, which
are called higher-order tensors.
Matrices are tensors of order two.
By definition, a matrix is rank-1 if its columns (or equivalently, rows) are proportional.
A ...
Compression-based and updating algorithms for constrained decompositions: explicitly and implicitly given tensors KU Leuven
Almost all fields in science and engineering rely on data to analyze phenomena, predict events, discover hidden patterns, etc. While tools based on matrices have been very successful, only two modes are taken into account. In contrast, techniques for multiway arrays of numbers, or tensors, can handle three or more modes, often leading to more compact and more interpretable models.
We develop a proximal optimization algorithm for ...