Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915126590832640 |
|---|---|
| author | Cybiński, Kacper Płodzień, Marcin Tomza, Michał Lewenstein, Maciej Dauphin, Alexandre Dawid, Anna |
| author_facet | Cybiński, Kacper Płodzień, Marcin Tomza, Michał Lewenstein, Maciej Dauphin, Alexandre Dawid, Anna |
| contents | Machine learning (ML) is a promising tool for the detection of phases of matter. However, ML models are also known for their black-box construction, which hinders understanding of what they learn from the data and makes their application to novel data risky. Moreover, the central challenge of ML is to ensure its good generalization abilities, i.e., good performance on data outside the training set. Here, we show how the informed use of an interpretability method called class activation mapping (CAM), and the analysis of the latent representation of the data with the principal component analysis (PCA) can increase trust in predictions of a neural network (NN) trained to classify quantum phases. In particular, we show that we can ensure better out-of-distribution generalization in the complex classification problem by choosing such an NN that, in the simplified version of the problem, learns a known characteristic of the phase. We show this on an example of the topological Su-Schrieffer-Heeger (SSH) model with and without disorder, which turned out to be surprisingly challenging for NNs trained in a supervised way. This work is an example of how the systematic use of interpretability methods can improve the performance of NNs in scientific problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10012 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model Cybiński, Kacper Płodzień, Marcin Tomza, Michał Lewenstein, Maciej Dauphin, Alexandre Dawid, Anna Quantum Physics Disordered Systems and Neural Networks Machine learning (ML) is a promising tool for the detection of phases of matter. However, ML models are also known for their black-box construction, which hinders understanding of what they learn from the data and makes their application to novel data risky. Moreover, the central challenge of ML is to ensure its good generalization abilities, i.e., good performance on data outside the training set. Here, we show how the informed use of an interpretability method called class activation mapping (CAM), and the analysis of the latent representation of the data with the principal component analysis (PCA) can increase trust in predictions of a neural network (NN) trained to classify quantum phases. In particular, we show that we can ensure better out-of-distribution generalization in the complex classification problem by choosing such an NN that, in the simplified version of the problem, learns a known characteristic of the phase. We show this on an example of the topological Su-Schrieffer-Heeger (SSH) model with and without disorder, which turned out to be surprisingly challenging for NNs trained in a supervised way. This work is an example of how the systematic use of interpretability methods can improve the performance of NNs in scientific problems. |
| title | Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model |
| topic | Quantum Physics Disordered Systems and Neural Networks |
| url | https://arxiv.org/abs/2406.10012 |