Migrating Knowledge between Physical Scenarios based on Artificial Neural Networks
This addresses the challenge of limited datasets in scientific applications by enabling knowledge transfer, though it is incremental as it applies existing transfer learning methods to new physical domains.
The paper tackles the problem of deep learning's data-hungry nature in science by using transfer learning to migrate knowledge between physical scenarios, reducing relative error rates by up to 46.8% in photonic film predictions and 22% between different scenarios.
Deep learning is known to be data-hungry, which hinders its application in many areas of science when datasets are small. Here, we propose to use transfer learning methods to migrate knowledge between different physical scenarios and significantly improve the prediction accuracy of artificial neural networks trained on a small dataset. This method can help reduce the demand for expensive data by making use of additional inexpensive data. First, we demonstrate that in predicting the transmission from multilayer photonic film, the relative error rate is reduced by 46.8% (26.5%) when the source data comes from 10-layer (8-layer) films and the target data comes from 8-layer (10-layer) films. Second, we show that the relative error rate is decreased by 22% when knowledge is transferred between two very different physical scenarios: transmission from multilayer films and scattering from multilayer nanoparticles. Finally, we propose a multi-task learning method to improve the performance of different physical scenarios simultaneously in which each task only has a small dataset.