5 citations · 13 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022
Fitting an immersed submanifold to data via Sussmann's orbit theorem
Joshua Hanson, Maxim Raginsky
This paper describes an approach for fitting an immersed submanifold of a finite-dimensional Euclidean space to random samples. The reconstruction mapping from the ambient space to…
cs.LG2020★ 4 cited
Learning Recurrent Neural Net Models of Nonlinear Systems
Joshua Hanson, Maxim Raginsky, Eduardo Sontag
We consider the following learning problem: Given sample pairs of input and output signals generated by an unknown nonlinear system (which is not assumed to be causal or time-invar…
cs.LG2019★ 4 cited
Universal Approximation of Input-Output Maps by Temporal Convolutional Nets
Joshua Hanson, Maxim Raginsky
There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in traini…