Titel Deelnemers "Korte inhoud" "Improving the performance of machine learning models for biotechnology : the quest for deus ex machina" "Friederike Mey, Jim Clauwaert, Kirsten Van Huffel, Willem Waegeman, Marjan De Mey" "Machine learning is becoming an integral part of the Design-Build-Test-Learn cycle in biotechnology. Machine learning models learn from collected datasets such as omics data and predict a defined outcome, which has led to both production improvements and predictive tools in the field. Robust prediction of the behavior of microbial cell factories and production processes not only greatly increases our understanding of the function of such systems, but also provides significant savings of development time. However, many pitfalls when modeling biological data - bad fit, noisy data, model instability, low data quantity and imbalances in the data - cause models to suffer in their performance. Here we provide an accessible, in-depth analysis on the problems created by these pitfalls, as well as means of their detection and mediation, with a focus on supervised learning. Assessing the state of the art, we show that, currently, in-depth analyses of model performance are often absent and must be improved. This review provides a toolbox for the analysis of model robustness and performance, and simultaneously proposes a standard for the community to facilitate future work. It is further accompanied by an interactive online tutorial on the discussed issues." "Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learning" "Fabian Böhm, Diego Alonso-Urquijo Iruarrizaga, Guy Verschaffelt, Guy Van Der Sande" "Ising machines are a promising non-von-Neumann computational concept for neural network training and combinatorial optimization. However, while various neural networks can be implemented with Ising machines, their inability to perform fast statistical sampling makes them inefficient for training neural networks compared to digital computers. Here, we introduce a universal concept to achieve ultrafast statistical sampling with analog Ising machines by injecting noise. With an opto-electronic Ising machine, we experimentally demonstrate that this can be used for accurate sampling of Boltzmann distributions and for unsupervised training of neural networks, with equal accuracy as software-based training. Through simulations, we find that Ising machines can perform statistical sampling orders-of-magnitudes faster than software-based methods. This enables the use of Ising machines beyond combinatorial optimization and makes them into efficient tools for machine learning and other applications." "Ultrafast Boltzmann Sampling using Photonic Ising Machines for Machine Learning" "Guy Van Der Sande, Fabian Böhm, Diego Alonso-Urquijo Iruarrizaga, Guy Verschaffelt" "Ising machines have emerged as a promising computational concept that specializes in solving resource intensive optimization problems. Their operation is based on mapping a problem’s cost function to a network of coupled Ising spins whose energy is described by the Ising Hamiltonian. Such a spin system can be emulated on a network of bistable analog oscillators and the tendency of this system to evolve to the lowest energy configuration is then used to find optimal solutions of a problem orders of magnitude faster than digital computers. In optics, photonic Ising machines based on coupled lasers, degenerate optical parametric oscillators and polariton condensates have recently demonstrated potential performance gains over digital hardware. As an alternative to these complex systems, we have developed a photonic Ising machine based on opto-electronic oscillators [1], which can utilize telecom-grade components and potentially yields high bandwidths of 40 GHz. We have shown that this opto-electronic Ising machine can have similar and in specific cases even significantly better performance on solving combinatorial optimization tasks as compared to the state of the art." "The detection of generator bearing failures on wind turbines using machine learning based anomaly detection" "In this research an early warning methodological framework is developed that is able to detect premature failures due to excessive wear. The methodology follows the data-driven Normal Behavior Model (NBM) principle, in which one or more data-driven models are used to model the normal behavior of the wind turbine. Anomalous behaviour of the turbine is identified by analyzing the deviation between the observed and predicted normal behaviour. The framework consists of two pipelines, a statistics and machine learning based pipeline. The former is based on techniques like ARIMA, OLS and CUSUM. The latter makes use of techniques like Random Forest, Gradient Boosting, … Each pipeline has its strengths and weaknesses, but by combining them in an intelligent way, a more capable detector is developed. The methodology is validated on 10-minute SCADA data from a real operational wind farm. The validation case focuses on generator (front/rear) bearing failures. The goal is to predict these failures well in advance (ideally at least a month) using the developed framework, which should allow for timely adjustments to the maintenance plan. The results show that the methodology is able to accomplish this reliably." "Detection of cleaning interventions on photovoltaic modules with machine learning" "Matthias Heinrich, Simon Meunier, Allou Same, Loic Queval, Arouna Darga, Latifa Oukhellou, Bernard Multon" "Virtual training of machine learning algorithm using a multibody model for bearing diagnostics on independent cart system" "Tommaso Tamarozzi" "Embedding metric learning into an extreme learning machine for scene recognition" "Chen Wang, Guohua Peng, Bernard De Baets" "A review of machine learning and deep learning applications in wave energy forecasting and WEC optimization" "Alireza Shadmani, Mohammad Reza Nikoo, Amir H. Gandomi, Ruo-Qian Wang, Behzad Golparvar" "MosAIc: A Classical Machine Learning Multi-Classifier Based Approach against Deep Learning Classifiers for Embedded Sound Classification" "Lancelot Charles Lhoest, Mimoun Lamrini, Jurgen Vandendriessche, Nick Wouters, Bruno da Silva, Mohamed Yassin Chkouri, Abdellah Touhafi" "Environmental Sound Recognition has become a relevant application for smart cities. Such an application, however, demands the use of trained machine learning classifiers in order to categorize a limited set of audio categories. Although classical machine learning solutions have been proposed in the past, most of the latest solutions that have been proposed toward automated and accurate sound classification are based on a deep learning approach. Deep learning models tend to be large, which can be problematic when considering that sound classifiers often have to be embedded in resource constrained devices. In this paper, a classical machine learning based classifier called MosAIc, and a lighter Convolutional Neural Network model for environmental sound recognition, are proposed to directly compete in terms of accuracy with the latest deep learning solutions. Both approaches are evaluated in an embedded system in order to identify the key parameters when placing such applications on constrained devices. The experimental results show that classical machine learning classifiers can be combined to achieve similar results to deep learning models, and even outperform them in accuracy. The cost, however, is a larger classification time" "Do not sleep on traditional machine learning simple and interpretable techniques are competitive to deep learning for sleep scoring" "Jeroen Van Der Donckt, Jonas Van Der Donckt, Emiel Deprost, Michael Rademaker, Gilles Vandewiele, Sofie Van Hoecke"