paper-with-me

홈 › Papers

Generalization capabilities of translationally equivariant neural networks

2021-03-26 · Srinath Bulusu, Matteo Favoni, Andreas Ipp, David I. Müller, Daniel Schuh

The rising adoption of machine learning in high energy physics and lattice field theory necessitates the re-evaluation of common methods that are widely used in computer vision, which, when applied to problems in physics, can lead to significant drawbacks in terms of performance and generalizability. One particular example for this is the use of neural network architectures that do not reflect the underlying symmetries of the given physical problem. In this work, we focus on complex scalar field theory on a two-dimensional lattice and investigate the benefits of using group equivariant convolutional neural network architectures based on the translation group. For a meaningful comparison, we conduct a systematic search for equivariant and non-equivariant neural network architectures and apply them to various regression and classification tasks. We demonstrate that in most of these tasks our best equivariant architectures can perform and generalize significantly better than their non-equivariant counterparts, which applies not only to physical parameters beyond those represented in the training set, but also to different lattice sizes.

📄 PDF Abstract BibTeX arXiv:2103.14686

Code (1)

https://gitlab.com/openpixi/scalar_ml 공식 구현 pytorch

Tasks

Translation

Similar Papers 제목 키워드 기반

Generalization capabilities of neural networks in lattice applications

2021-12-23 · Srinath Bulusu, Matteo Favoni, Andreas Ipp, David I. Müller 외

In recent years, the use of machine learning has become increasingly popular in the context of lattice field theories. An essential element of such theories is represented by symmetries, whose inclusion in the neural net…

Equivariant Wavelets: Fast Rotation and Translation Invariant Wavelet Scattering Transforms

2021-04-22 · Andrew K. Saydjari, Douglas P. Finkbeiner

Wavelet scattering networks, which are convolutional neural networks (CNNs) with fixed filters and weights, are promising tools for image analysis. Imposing symmetry on image statistics can improve human interpretability…

Dimensionality ReductionTranslation

Equivariant neural networks for inverse problems

2021-02-23 · Elena Celledoni, Matthias J. Ehrhardt, Christian Etmann, Brynjulf Owren 외

In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of r…

Inductive Bias

E(n) Equivariant Message Passing Cellular Networks

2024-06-05 · Veljko Kovač, Erik J. Bekkers, Pietro Liò, Floor Eijkelboom

This paper introduces E(n) Equivariant Message Passing Cellular Networks (EMPCNs), an extension of E(n) Equivariant Graph Neural Networks to CW-complexes. Our approach addresses two aspects of geometric message passing n…

Scale Equivariant U-Net

2022-10-10 · Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo

In neural networks, the property of being equivariant to transformations improves generalization when the corresponding symmetry is present in the data. In particular, scale-equivariant networks are suited to computer vi…

Cell SegmentationSegmentationSemantic Segmentation