Some shapes look different to us if rotated. That is attributed to the use of a rotation frame of coordinates in the human visual system. However, no evidence that ConvNets, which is a machine learning architecture, use a frame of coordinates for rotation. We investigated the effect of adding one to ConvNets. An explicit orientation encoding kernel was developed using a mathematically inspired self-supervised approach. The experimental results showed that rotation encoding improved the accuracy of classifying rotated images and the resilience against noise.

Smiling differences between men and women have been studied in psychology. Women smile more than men although the expressiveness of women is not universally more across all facial actions. There are also body movement differences between women and men. For example, more open-body postures were reported for men, but are there any body-movement differences between men and women when they laugh? To investigate this question, we study body-movement signals extracted from recorded laughter videos using a deep learning pose estimation model.

In this paper, we deal with the problem of shadow detection of
UAVs, which impacts their navigation.

Since the introduction of Simulated Annealing (SA), researchers have considered variants that keep the same temperature value throughout the whole search and tried to determine whether this strategy can be more effective than the original cooling scheme. Several studied have tried to answer this question without a conclusive answer and without providing indications that could be useful for a practical implementation.

Neural network pruning is a widely used strategy for reducing model storage and computing requirements. It allows to lower the complexity of the network by introducing sparsity in the weights. Because taking advantage of sparse matrices is still challenging, pruning is often performed in a structured way, i.e. removing entire convolution filters in the case of ConvNets, according to a chosen pruning criteria.

The number of daily credit card transactions is inexorably growing: the e-commerce market expansion and the recent constraints for the Covid-19 pandemic have significantly increased the use of electronic payments. The ability to precisely detect fraudulent transactions is increasingly important, and machine learning models are now a key component of the detection process. Standard machine learning techniques are widely employed, but inadequate for the evolving nature of customers behavior entailing continuous changes in the underlying data distribution.

The limitation of transmission lines thermal capacity plays a crucial role in the safety and reliability of power systems. Dynamic thermal line rating approaches aim to estimate the transmission line’s temperature and assess its compliance with the limitations above. Existing physics-based standards estimate the temperature based on environment and line conditions measured by several sensors. This manuscript shows that estimation accuracy can be improved by adopting a data-driven Digital Twin approach.

Nous proposons une variable ciblant les problèmes de tournées de véhicules : la variable de séquence. La représentation de son domaine permet une recherche sur base d’insertions dans une route partiellement formée, ainsi que l’implémentation d’algorithmes simples, mais puissants, permettant de respecter des temps de transition entre les visites ou des capacités dans un véhicule. Nos expériences démontrent que cette variable est suffisamment flexible pour modéliser des problèmes d’itinéraires très contraints, tout en les résolvant de manière efficace.

Training recurrent neural networks is known to be difficult when time dependencies become long. Consequently, training standard gated cells such as the gated recurrent unit (GRU) and the long short-term memory (LSTM) on benchmarks where long-term memory is required remains an arduous task. In this work, we show that although most classical networks have only one stable equilibrium at initialisation, learning on tasks that require long-term memory only occurs once the number of network stable equilibria increases; a property known as multistability.