Deep learning for Chemometric and non-translational data
This addresses a domain-specific challenge in chemometrics where traditional data augmentation is not feasible, though it appears incremental in scope.
The paper tackles the problem of training deep convolutional neural networks on chemometric data with varying input sizes where signals cannot be translated or resized, proposing a weight-sharing method that shows superior performance to transfer learning for medium and small datasets and reduces variance for medium datasets.
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.