Colour-thresholding digital imaging methods are generally accurate for measuring the percentage of foliar area affected by disease or pests (severity), but they perform poorly when scene illumination and background are not uniform. In this study, six convolutional neural network (CNN) architectures were trained for semantic segmentation in images o...
Ce rapport porte sur un stage de 8 semaines effectué avec l’équipe Inria Mnemosyne travaillant sur l’action exploratoire AIDE (Artificial Intelligence Devoted to Education), et coencadré par Thierry Viéville et Chloé Mercier. Le cadre restait assez libre et peu défini, mais invitait à chercher à définir la notion de probabilité/nécessité étendue pr...
The pricing of Bermudan options amounts to solving a dynamic programming principle, in which the main difficulty, especially in high dimension, comes from the conditional expectation involved in the computation of the continuation value. These conditional expectations are classically computed by regression techniques on a finite dimensional vector ...
Hlavním úkolem diplomové práce "Předpovídání časových sérií s využitím rekurentních neuronových sítí" je natrénovat modely na časových sériích dat, které se následně porovnávají a využijí v aplikaci. / The main subject of the diploma thesis “Time series forecasting with recurrent neural networks” is to train models on typical time series data compa...
We analyzed the influence of the stratification process in the vertical distribution of larval fish in a microtidal coastal Mediterranean zone. By applying a Self Organizing Maps (SOM) technique, we could analyze a complex dataset accounting for non-linear processes. The analysis integrated multivariate data on larval fish and environmental paramet...
Outstanding seizure detection algorithms using electroencephalogram (EEG) recordings have been developed over the past decade. These works mainly focus on best of class performance, which leads to computationally heavy solutions. This limits the applicability of these detection algorithms for hardware implementations such as fieldprogrammable gate...
Department of Mathematical Sciences / open
Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first-principles based virtual sampling of this space, for example, in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for al...
Published in Chemical reviews
We review progress in neural network (NN)-based methods for the construction of interatomic potentials from discrete samples (such as ab initio energies) for applications in classical and quantum dynamics including reaction dynamics and computational spectroscopy. The main focus is on methods for building molecular potential energy surfaces (PES) i...
We introduce and study an extension of the classical elapsed time equation in the context of neuron populations that are described by the elapsed time since the last discharge, i.e., the refractory period. In this extension we incorporate the elapsed since the penultimate discharge and we obtain a more complex system of integro-differential equatio...
