Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation

no code implementations • 23 Nov 2023 • Markus Gross, Arne P. Raulf, Christoph Räth

We investigate the stationary (late-time) training regime of single- and two-layer linear underparameterized neural networks within the continuum limit of stochastic gradient descent (SGD) for synthetic Gaussian data.

Deep Neural Networks for the Correction of Mie Scattering in Fourier-Transformed Infrared Spectra of Biological Samples

no code implementations • 18 Feb 2020 • Arne P. Raulf, Joshua Butke, Lukas Menzen, Claus Küpper, Frederik Großerueschkamp, Klaus Gerwert, Axel Mosig

Infrared spectra obtained from cell or tissue specimen have commonly been observed to involve a significant degree of (resonant) Mie scattering, which often overshadows biochemically relevant spectral information by a non-linear, non-additive spectral component in Fourier transformed infrared (FTIR) spectroscopic measurements.