Home /
Research
Showing 409 - 414 / 904
Deep Reinforcement Learning for Feedback Control in a Collective Flashing Ratchet
Dong-KyumKim, HawoongJeong....
Published date-11/20/2020
A collective flashing ratchet transports Brownian particles using a spatially periodic, asymmetric, and time-dependent on-off switchable potential. The net current of the particles in this system can be substantially increased …
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 …
Graph Signal Recovery Using Restricted Boltzmann Machines
AnkithMohan, AiichiroNakano, EmilioFerrara....
Published date-11/20/2020
Denoising
We propose a model-agnostic pipeline to recover graph signals from an expert system by exploiting the content addressable memory property of restricted Boltzmann machine and the representational ability of a …
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
XingeZhu, HuiZhou, TaiWang....
Published date-11/19/2020
3DSemanticSegmentation, PanopticSegmentation
State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the …
Interpretable and Transferable Models to Understand the Impact of Lockdown Measures on Local Air Quality
JohannaEinsiedler, YunCheng, FranzPapst....
Published date-11/19/2020
TransferLearning
The COVID-19 related lockdown measures offer a unique opportunity to understand how changes in economic activity and traffic affect ambient air quality and how much pollution reduction potential can the …
Finding the Homology of Decision Boundaries with Active Learning
WeizhiLi, GautamDasarathy, KarthikeyanNatesanRamamurthy....
Published date-11/19/2020
ActiveLearning, Meta-Learning, ModelSelection, TopologicalDataAnalysis
Accurately and efficiently characterizing the decision boundary of classifiers is important for problems related to model selection and meta-learning. Inspired by topological data analysis, the characterization of decision boundaries using …