output
20022022
most citedEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

10.8k citations

Showing 2019Show all

41 papers · 1 filter

cond-mat.mtrl-sci201915 cited

Enhanced nonlinear interaction of polaritons via excitonic Rydberg states in monolayer WSe2

Jie Gu, Valentin Walther, Lutz Waldecker +7

Strong optical nonlinearities play a central role in realizing quantum photonic technologies. In solid state systems, exciton-polaritons, which result from the hybridization of mat…

cs.CR20194 cited

SIGMA : Strengthening IDS with GAN and Metaheuristics Attacks

Simon Msika, Alejandro Quintero, Foutse Khomh

An Intrusion Detection System (IDS) is a key cybersecurity tool for network administrators as it identifies malicious traffic and cyberattacks. With the recent successes of machine…

cs.LG201914 cited

Real-Time Reinforcement Learning

Simon Ramstedt, Christopher Pal

Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the sta…

cs.LG20191 cited

Training Modern Deep Neural Networks for Memory-Fault Robustness

Ghouthi Boukli Hacene, François Leduc-Primeau, Amal Ben Soussia +2

Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging. In this paper, we inve…

cs.LG20193 cited

Neural Multisensory Scene Inference

Jae Hyun Lim, Pedro O. Pinheiro, Negar Rostamzadeh +2

For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e.g., by look…

math.OC20191 cited

StoMADS: Stochastic blackbox optimization using probabilistic estimates

Charles Audet, Kwassi Joseph Dzahini, Michael Kokkolaras +1

This work introduces StoMADS, a stochastic variant of the mesh adaptive direct-search (MADS) algorithm originally developed for deterministic blackbox optimization. StoMADS conside…