Publications
Chosen filters:
Chosen filters:
Reservoir Computing for Intelligent Mobile Systems (Reservoir Computing voor intelligente mobiele systemen) KU Leuven
Op het gebied van artificiële intelligentie, zijn artificiële neurale ne twerken (ANNs) een interessant hulpmiddel: ze bieden goede prestaties en kunnen worden toegepast op problemen waarvoor de directe oplossing niet bekend is. Inderdaad, ANNs kunnen worden getrained door voorbeelden. On der ANNs, recurrente neurale netwerken (RNNs) zijn bijzonder goed geschi kt voor taken die een tijdscomponent inhouden, vermits hun terugkerende lussen hen ...
Cladoceran community composition in tropical semi-arid highland reservoirs in Tigray (Northern Ethiopia): A metacommunity perspective applied to young reservoirs KU Leuven
A field survey of zooplankton communities was carried out in 32 recently established tropical semi-arid reservoirs in the highlands of Northern Ethiopia with the aim to identify to what extent environmental factors determine species composition of the cladoceran community in such isolated and young reservoirs. To address seasonal variation, the survey was carried out both at the beginning and the end of the dry season. A total of 15 species of ...
Establishment of latent HIV-1 reservoirs : what do we really know? Ghent University KU Leuven
Pattern classification with CNNs as reservoirs Ghent University
Reservoir Computing is a novel method in the field of neural networks and machine learning, which combines the computational power of a nonlinear dynamic system with the ease of training of a linear classifier. The basic setup is as follows: a sufficiently complex network of nonlinear nodes (called the reservoir) is excited by an input signal, and the instantaneous dynamic response of the system is then used to train a simple linear readout ...
Continuous digit recognition in noise: reservoirs can do an excellent job! Ghent University
In this paper a formerly proposed continuous digit recognition system based on Reservoir Computing (RC) is improved in two respects: (1)the single reservoir is substituted by a stack of reservoirs, and (2)the straightforward mapping of reservoir outputs to state likelihoods is replaced by a trained non-parametric mapping. Furthermore, it is shown that a reservoir-based method can improve a model trained on clean speech to work better in a noisy ...
Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs Ghent University
As the performance increase of traditional Von-Neumann computing attenuates, new approaches to computing need to be found. A promising approach for low-power computing at high bitrates is integrated photonic reservoir computing. In the past though, the feasible reservoir size and computational power of integrated photonic reservoirs have been limited by hardware constraints. An alternative solution to building larger reservoirs is the ...
Research hotspots and current challenges of lakes and reservoirs : a bibliometric analysis Ghent University
The study of trypanosome species circulating in domestic animals in two human African trypanosomiasis foci of Côte d'Ivoire identifies pigs and cattle as potential reservoirs of Trypanosoma brucei gambiense Institute of Tropical Medicine
BACKGROUND: Important control efforts have led to a significant reduction of the prevalence of human African trypanosomiasis (HAT) in Côte d'Ivoire, but the disease is still present in several foci. The existence of an animal reservoir of Trypanosoma brucei gambiense may explain disease persistence in these foci where animal breeding is an important source of income but where the prevalence of animal African trypanosomiasis (AAT) is unknown. ...