Deep learning for Chemometric and non-translational data

TL;DR

This paper introduces a new deep learning method that effectively trains convolutional neural networks on multiple chemometric datasets with varying input sizes, outperforming transfer learning especially with small datasets.

Contribution

A novel weight sharing approach enabling CNN training on datasets of different sizes without translation, improving performance in chemometric applications.

Findings

Outperforms transfer learning with mixed datasets

Reduces variance when training on medium-sized datasets

Shows small improvements with combined medium datasets

Abstract

We propose a novel method to train deep convolutional neural networks which learn from multiple data sets of varying input sizes through weight sharing. This is an advantage in chemometrics where individual measurements represent exact chemical compounds and thus signals cannot be translated or resized without disturbing their interpretation. Our approach show superior performance compared to transfer learning when a medium sized and a small data set are trained together. While we observe a small improvement compared to individual training when two medium sized data sets are trained together, in particular through a reduction in the variance.