Publications
Chosen filters:
Chosen filters:
Opportunities and challenges for the sustainability of lakes and reservoirs in relation to the sustainable development goals (SDGs) Ghent University
Emerging global threats, such as biological invasions, climate change, land use intensification, and water depletion, endanger the sustainable future of lakes and reservoirs. To deal with these threats, a multidimensional view on the protection and exploitation of lakes and reservoirs is needed. The holistic approach needs to contain not just the development of economy and society but also take into account the negative impacts of this growth on ...
Using photonic reservoirs as preprocessors for deep neural networks Ghent University Vrije Universiteit Brussel
Artificial neural networks are very time consuming and energy intensive to train, especially when increasing the size of the neural network in an attempt to improve the performance. In this paper, we propose to preprocess the input data of a deep neural network using a reservoir, which has originally been introduced in the framework of reservoir computing. The key idea of this paper is to use such a reservoir to transform the input data into a ...
Audio classification with skyrmion reservoirs Ghent University
Physical reservoir computing is a computational paradigm that enables spatiotemporal pattern recognition to be performed directly in matter. The use of physical matter leads the way toward energy-efficient devices capable of solving machine learning problems without having to build a system of millions of interconnected neurons. Proposed herein is a high-performance "skyrmion mixture reservoir" that implements the reservoir computing model with ...
Memory versus non-linearity in reservoirs Ghent University
Reservoir Computing (RC) is increasingly being used as a conceptually simple yet powerful method for using the temporal processing of recurrent neural networks (RNN). However, because fundamental insight in the exact functionality of the reservoir is as yet still lacking, in practice there is still a lot of manual parameter tweaking or brute-force searching involved in optimizing these systems. In this contribution we aim to enhance the insights ...
In-depth single-cell analysis of translation-competent HIV-1 reservoirs identifies cellular sources of plasma viremia Ghent University
Clonal expansion of HIV-infected cells contributes to the long-term persistence of the HIV reservoir in ART-suppressed individuals. However, the contribution from cell clones that harbor inducible proviruses to plasma viremia is poorly understood. Here, we describe a single-cell approach to simultaneously sequence the TCR, integration sites and proviral genomes from translation-competent reservoir cells, called STIP-Seq. By applying this ...
Training passive photonic reservoirs with integrated optical readout Ghent University
As Moore's law comes to an end, neuromorphic approaches to computing are on the rise. One of these, passive photonic reservoir computing, is a strong candidate for computing at high bitrates (>10 Gb/s) and with low energy consumption. Currently though, both benefits are limited by the necessity to perform training and readout operations in the electrical domain. Thus, efforts are currently underway in the photonic community to design an ...
Phoneme recognition with large hierarchical reservoirs Ghent University
Automatic speech recognition has gradually improved over the years, but the reliable recognition of unconstrained speech is still not within reach. In order to achieve a breakthrough, many research groups are now investigating new methodologies that have potential to outperform the Hidden Markov Model technology that is at the core of all present commercial systems. In this paper, it is shown that the recently introduced concept of Reservoir ...
The spectral radius remains a valid indicator of the echo state property for large reservoirs Ghent University
In the field of Reservoir Computing, scaling the spectral radius of the weight matrix of a random recurrent neural network to below unity is a commonly used method to ensure the Echo State Property. Recently it has been shown that this condition is too weak. To overcome this problem, other more involved - sufficient conditions for the Echo State Property have been proposed. In this paper we provide a large-scale experimental verification of the ...
Phytoplankton community structure and cyanobacterial blooms in reservoirs in the semi-arid highlands of Tigray, Ethiopia Ghent University
Ethiopia is the third largest country in Africa with an area of over one million km2. It is one of the most populous countries in Africa (probably second), with more than 80 million inhabitants. The Ethiopian highlands represent about 43% of the country but support about 88% of the population. The highlands account for 95% of the regularly cropped land, more that 70% of the livestock population, and 90% of the economic activities of the country. ...