Published in Autonomous Agents and Multi-Agent Systems
Reinforcement Learning (RL) agents are commonly thought of as adaptive decision procedures. They work on input/output data streams called “states”, “actions” and “rewards”. Most current research about RL adaptiveness to changes works under the assumption that the streams signatures (i.e. arity and types of inputs and outputs) remain the same throug...
Self-driving vehicles need to continuously analyse the driving scene, understand the behavior of other road users and predict their future trajectories in order to plan a safe motion and reduce their reaction time. Motivated by this idea, this paper addresses the problem of vehicle trajectory prediction over an extended horizon. On highways, human ...
A side-channel attack is performed by analyzing unwanted physical leakage to achieve a more effective attack on the cryptographic key. An attacker performs a profiled attack when he has a physical and identical copy of the target device, meaning the attacker is in full control of the target device. Therefore, these profiled attacks are known as the...
Spacecraft require high availability, autonomous operation, and a high degree of mission success. Spacecraft use sensors, such as star trackers and GPS, and actuators, such as reaction wheels, to reach and maintain a correct attitude and position. Failures in these components will have a significant negative impact on the success of the mission, or...
Published in NeuroImage
Many recent advances in artificial intelligence (AI) are rooted in visual neuroscience. However, ideas from more complicated paradigms like decision-making are less used. Although automated decision-making systems are ubiquitous (driverless cars, pilot support systems, medical diagnosis algorithms etc.), achieving human-level performance in decisio...
The advent of multitemporal high resolution data, like theCopernicus Sentinel-2, has enhanced significantly the poten-tial of monitoring the earth’s surface and environmental dy-namics. In this paper, we present a novel deep learning frame-work for urban change detection which combines state-of-the-art fully convolutional networks (similar to U-Net...
Published in The Journal of Mathematical Neuroscience
We examine a family of random firing-rate neural networks in which we enforce the neurobiological constraint of Dale’s Law—each neuron makes either excitatory or inhibitory connections onto its post-synaptic targets. We find that this constrained system may be described as a perturbation from a system with nontrivial symmetries. We analyze the symm...
Over the past several years, deep and wide neural networks have achieved great success in many tasks. However, in real life applications, because the gains usually come at a cost in terms of the system resources (e.g., memory, computation and power consumption), it is impractical to run top-performing but heavy networks such as VGGNet and GoogleNet...
Published in Neural networks : the official journal of the International Neural Network Society
In this paper, we study how the dynamics of recurrent networks, formulated as general dynamical systems, mediate the recovery of sparse, time-varying signals. Our formulation resembles the well-described problem of compressed sensing, but in a dynamic setting. We specifically consider the problem of recovering a high-dimensional network input, over...
The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining featur...
