We have recently seen great progress in learning interpretable music representations, ranging from basic factors, such as pitch and timbre, to high-level concepts, such as chord and texture. However, most methods rely heavily on music domain knowledge. It remains an open question what general computational principles give rise to interpretable representations, especially low-dim factors that agree with human perception. In this study, we take inspiration from modern physics and use physical symmetry as a self consistency constraint for the latent space of time-series data. Specifically, it requires the prior model that characterises the dynamics of the latent states to be equivariant with respect to certain group transformations. We show that physical symmetry leads the model to learn a linear pitch factor from unlabelled monophonic music audio in a self-supervised fashion. In addition, the same methodology can be applied to computer vision, learning a 3D Cartesian space from videos of a simple moving object without labels. Furthermore, physical symmetry naturally leads to counterfactual representation augmentation, a new technique which improves sample efficiency.
Physically Interpretable Representation Learning with Gaussian Mixture Variational AutoEncoder (GM-VAE)
Institute for Computational and Mathematical Engineering, Stanford University(计算与数学工程研究所,斯坦福大学);Department of Mechanical Engineering, Stanford University(机械工程系,斯坦福大学);National Renewable Energy Laboratory(国家可再生能源实验室);Ann and H.J. Smead Department of Aerospace Engineering Sciences, University of Colorado, Boulder(安与H.J.斯迈德航空航天工程科学系,科罗拉多大学,博尔德)
TIME: A Transparent, Interpretable, Model-Adaptive and Explainable Neural Network for Dynamic Physical Processes
Oden Institute for Computational Engineering and Sciences(奥登计算工程与科学研究所);Department of Computer Science(计算机科学系);School of Information(信息学院);University of Texas, Austin(得克萨斯大学奥斯汀分校)
Can Data-Driven Dynamics Reveal Hidden Physics? There Is A Need for Interpretable Neural Operators
Department of Applied Mathematics and Statistics, Stony Brook University(应用数学与统计学系,石英布鲁克大学);Department of Computer Science, Stony Brook University(计算机科学系,石英布鲁克大学)
PILA: Physics-Informed Low Rank Augmentation for Interpretable Earth Observation
Department of Computer Science and Technology, University of Cambridge(计算机科学与技术系,剑桥大学);Clare Hall, University of Cambridge(剑桥大学克莱尔学院);Cyclops AI;Department of Earth Sciences, University of Cambridge(地球科学系,剑桥大学)
OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学);Princeton University(普林斯顿大学);National University of Singapore(新加坡国立大学);Institute of High Performance Computing, A*STAR(A*STAR高性能计算研究院)
Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
Sapienza University of Roma(罗马第一大学);Radboud University(拉德堡德大学);Saddle Point Science Europe(鞍点科学欧洲研究院)
Insights on Galaxy Evolution from Interpretable Sparse Feature Networks
Space Telescope Science Institute, 3700 San Martin Dr, Baltimore, MD 21218;Department of Physics \& Astronomy, Johns Hopkins University, 3400 N Charles St, Baltimore, MD 21218;Department of Computer Science, Johns Hopkins University, 3400 N Charles St, Baltimore, MD 21218
Hybrid Physical-Deep Learning Model for Astronomical Inverse Problems
Berkeley Center for Cosmological Physics(伯克利宇宙物理中心);Berkeley Institute for Data Science(伯克利数据科学研究所);University of California, Berkeley(加州大学伯克利分校);Department of Astrophysical Sciences(天体物理科学系);Center for Statistics and Machine Learning(统计与机器学习中心);Princeton University(普林斯顿大学);LSST Project Management Office(大口径全天巡视望远镜项目管理办公室)
Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
Cornell University(康奈尔大学);Harvard University(哈佛大学);Technical University of Munich(慕尼黑工业大学);Institute for Advanced Study(高等研究院);Munich Center for Quantum Science and Technology(慕尼黑量子科学与技术中心);Princeton University(普林斯顿大学)
LieAugmenter: Equivariant Learning by Discovering Symmetries with Learnable Augmentations
Technical University of Munich (School of CIT)(慕尼黑技术大学);Munich Center for Machine Learning(慕尼黑机器学习中心);Munich Data Science Institute(慕尼黑数据科学研究所);MIT (Department of EECS and CSAIL)(麻省理工学院)