Home /
Research
Showing 403 - 408 / 904
Self-Supervised Small Soccer Player Detection and Tracking
SamuelHurault, ColomaBallester, GloriaHaro....
Published date-11/20/2020
In a soccer game, the information provided by detecting and tracking brings crucial clues to further analyze and understand some tactical aspects of the game, including individual and team actions. …
Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains, and applications
QuentinDuchemin, YohanndeCastro, ClaireLacour....
Published date-11/20/2020
We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains. Working with bounded $\pi$-canonical kernels, we show that we can recover the convergence rate …
Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks
ArnaudFanthomme, RémiMonasson....
Published date-11/20/2020
We study the learning dynamics and the representations emerging in Recurrent Neural Networks trained to integrate one or multiple temporal signals. Combining analytical and numerical investigations, we characterize the conditions …
Data-Driven System Level Synthesis
AntonXue, NikolaiMatni....
Published date-11/20/2020
We establish data-driven versions of the System Level Synthesis (SLS) parameterization of stabilizing controllers for linear-time-invariant systems. Inspired by recent work in data-driven control that leverages tools from behavioral theory, …
Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision
KwanseokOh, JeeSeokYoon, Heung-IlSuk....
Published date-11/20/2020
There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose Born Identity Network (BIN), which is …
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
RewonChild....
Published date-11/20/2020
ImageGeneration
We present a hierarchical VAE that, for the first time, outperforms the PixelCNN in log-likelihood on all natural image benchmarks. We begin by observing that VAEs can actually implement autoregressive …