71 citations · 97 across the 2 of their papers we have counts for
8 papers
Continuous-in-Depth Neural Networks
Alejandro F. Queiruga, N. Benjamin Erichson, Dane Taylor +1
Recent work has attempted to interpret residual networks (ResNets) as one step of a forward Euler discretization of an ordinary differential equation, focusing mainly on syntactic…
Error Estimation for Sketched SVD via the Bootstrap
Miles E. Lopes, N. Benjamin Erichson, Michael W. Mahoney
In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach. However,…
Forecasting Sequential Data using Consistent Koopman Autoencoders
Omri Azencot, N. Benjamin Erichson, Vanessa Lin +1
Recurrent neural networks are widely used on time series data, yet such models often ignore the underlying physical structures in such sequences. A new class of physics-based metho…
Bootstrapping the Operator Norm in High Dimensions: Error Estimation for Covariance Matrices and Sketching
Miles E. Lopes, N. Benjamin Erichson, Michael W. Mahoney
Although the operator (spectral) norm is one of the most widely used metrics for covariance estimation, comparatively little is known about the fluctuations of error in this norm.…
Randomized methods to characterize large-scale vortical flow network
Zhe Bai, N. Benjamin Erichson, Muralikrishnan Gopalakrishnan Meena +2
We demonstrate the effective use of randomized methods for linear algebra to perform network-based analysis of complex vortical flows. Network theoretic approaches can reveal the c…
Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
N. Benjamin Erichson, Michael Muehlebach, Michael W. Mahoney
In addition to providing high-profile successes in computer vision and natural language processing, neural networks also provide an emerging set of techniques for scientific proble…