paper-with-me

Papers

Deep Learning with Physics Priors as Generalized Regularizers

2023-12-14 · Frank Liu, Agniva Chowdhury

In various scientific and engineering applications, there is typically an approximate model of the underlying complex system, even though it contains both aleatoric and epistemic uncertainties. In this paper, we present a principled method to incorporate these approximate models as physics priors in modeling, to prevent overfitting and enhancing the generalization capabilities of the trained models. Utilizing the structural risk minimization (SRM) inductive principle pioneered by Vapnik, this approach structures the physics priors into generalized regularizers. The experimental results demonstrate that our method achieves up to two orders of magnitude of improvement in testing accuracy.

📄 PDF Abstract BibTeX arXiv:2312.08678

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Weak Form Generalized Hamiltonian Learning

2020-12-01 · NeurIPS 2020 12 · Kevin Course, Trefor Evans, Prasanth Nair

We present a method for learning generalized Hamiltonian decompositions of ordinary differential equations given a set of noisy time series measurements. Our method simultaneously learns a continuous time model and a sca…

FormTime SeriesTime Series Analysis

Weak Form Generalized Hamiltonian Learning

2021-04-11 · Kevin L. Course, Trefor W. Evans, Prasanth B. Nair

We present a method for learning generalized Hamiltonian decompositions of ordinary differential equations given a set of noisy time series measurements. Our method simultaneously learns a continuous time model and a sca…

FormTime SeriesTime Series Analysis

Training Deep Neural Classifiers with Soft Diamond Regularizers

2024-12-30 · Olaoluwa Adigun, Bart Kosko

We introduce new \emph{soft diamond} regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-dia…

Data Augmentation

High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks

2020-05-12 · Seyed Amir Hossein Hosseini, Burhaneddin Yaman, Steen Moeller, Mehmet Akçakaya

Long scan duration remains a challenge for high-resolution MRI. Deep learning has emerged as a powerful means for accelerated MRI reconstruction by providing data-driven regularizers that are directly learned from data. …

Deep LearningMRI ReconstructionTransfer Learning

Dynamic Regularizer with an Informative Prior

2019-10-31 · Avinash Kori, Manik Sharma

Regularization methods, specifically those which directly alter weights like $L_1$ and $L_2$, are an integral part of many learning algorithms. Both the regularizers mentioned above are formulated by assuming certain pri…