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.

Self-organised aggregation is one of the basic collective behaviours studied in swarm robotics. In this paper, we investigate an aggregation problem occurring on two different sites. Previous studies have shown that a minority of robots, informed about the site on which they have to aggregate, can control the final distribution of the entire robot swarm on the sites. We reproduce this strategy by adapting the previous probabilistic finite-state machine to a new simulated robotic platform: the Kilobot.

Self-organized aggregation is a well studied behavior in swarm robotics as it is the pre-condition for the development of more advanced group-level responses. In this paper, we investigate the design of decentralized algorithms for a swarm of heterogeneous robots that self-aggregate over distinct target sites. A previous study has shown that including as part of the swarm a number of informed robots can steer the dynamic of the aggregation process to a desirable distribution of the swarm between the available aggregation sites.

Strongly opinionated minorities can have a dramatic impact on the opinion dynamics of a large population. Two factions of inflexible minorities, polarised into two competing opinions, could lead the entire population to persistent indecision. Equivalently, populations can remain undecided when individuals sporadically change their opinion based on individual information rather than social information.

We study how robot swarms can achieve a consensus on the best among a set of n possible options available in the environment. While the robots rely on local communication with one another, follow simple rules, and make estimates of the option’s qualities subject to measurement errors, the swarm as a whole is able to make accurate collective decisions. We compare the performance of two prominent decision-making algorithms that are based, respectively, on the direct-switching and the cross-inhibition models, both of which are well-suited for simplistic robots.

In this paper, we study the exploitation of language generation models for disinformation purposes from two viewpoints. Quantitatively, we argue that language models hardly deal with domain adaptation (i.e., the ability to generate text on topics that are not part of a training database, as typically required for news). For this purpose, we show that both simple machine learning models and manual detection can spot machine-generated news in this practically-relevant context.

Améliorer la compréhension de la nature oligogénique des maladies requiert l'accès à des données de haute qualité, bien curée et FAIR (Findable, Accessible, Interoperable, Reusable). Bien que les premiers pas avaient été faits avec le développement de la Digenic Diseases Database, conduisant à des avancements computationels pour aider dans le domaine, ceux-ci étaient aussi liés à un nombre de limitations, par exemple, le protocol de curation ad hoc et l'inclusion de seulement les cas digéniques.

Recommendation Systems (RS) aim to help people deal with the information overload they face by recommending relevant items[ 4