output
19912026
most citedGeometric deep learning: going beyond Euclidean data

3.7k citations

Showing 2014Show all

99 papers · 1 filter

math.NA2014★ 31 cited

A fast and robust solver for the scattering from a layered periodic structure containing multi-particle inclusions

Jun Lai, Motoki Kobayashi, Alex Barnett

We present a solver for plane wave scattering from a periodic dielectric grating with a large number of inclusions lying in each period of its middle layer.Such composite mater…

cs.LG2014★ 296 cited

Video (language) modeling: a baseline for generative models of natural videos

MarcAurelio Ranzato, Arthur Szlam, Joan Bruna +3

We propose a strong baseline model for unsupervised feature learning using video data. By learning to predict missing frames or extrapolate future frames from an input video sequen…

physics.flu-dyn2014★ 37 cited

Low Mach Number Fluctuating Hydrodynamics of Multispecies Liquid Mixtures

A. Donev, A. J. Nonaka, A. K. Bhattacharjee +2

We develop a low Mach number formulation of the hydrodynamic equations describing transport of mass and momentum in a multispecies mixture of incompressible miscible liquids at spe…

cs.CV2014★ 11 cited

Unsupervised Learning of Spatiotemporally Coherent Metrics

Ross Goroshin, Joan Bruna, Jonathan Tompson +2

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coher…

physics.data-an2014★ 6 cited

Analog Forecasting with Dynamics-Adapted Kernels

Zhizhen Zhao, Dimitrios Giannakis

Analog forecasting is a nonparametric technique introduced by Lorenz in 1969 which predicts the evolution of states of a dynamical system (or observables defined on the states) by…

math.NT2014★ 8 cited

Partial sums of biased random multiplicative functions

Marco Aymone, Vladas Sidoravicius

Let be the set of the primes. We consider a class of random multiplicative functions supported on the squarefree integers, such that …