An official website of the United States government
Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregards frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.
more »
« less
This content will become publicly available on March 5, 2026
On understanding and overcoming spectral biases of deep neural network learning methods for solving PDEs
In this review, we survey the latest approaches and techniques developed to overcome the spectral bias towards low frequency of deep neural network learning methods in learning multiple frequency solutions of partial differential equations. Open problems and future research directions are also discussed.
more »
« less
- Award ID(s):
- 2207449
- PAR ID:
- 10647368
- Publisher / Repository:
- Elsevier Inc.
- Date Published:
- Journal Name:
- Journal of computational physics
- Volume:
- 530
- ISSN:
- 0021-9991
- Page Range / eLocation ID:
- 113905
- Subject(s) / Keyword(s):
- Neural networks Spectral bias Deep learning PDEs
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Cellular materials have been widely used in load carrying lightweight structures. Although lightweight increases natural frequency, low stiffness of cellular structures reduces natural frequency. Designing structures with higher natural frequency can usually avoid resonance. In addition, because of the less amount of materials used in cellular structures, the energy absorption capability usually decreases such as under impact loading. Therefore, designing cellular structures with higher natural frequency and higher energy absorption capability is highly desired. In this study, machine learning and novel inverse design techniques enable to search a huge space of unexplored structural designs. In this study, machine learning regression and Generative Neural Networks (GANs) were used to form an inverse design framework. Optimal cellular unit cells that surpass the performance of biomimetic structures inspired from honeycomb, plant stems and trabecular bone in terms of natural frequency and impact resistance were discovered using machine learning. The discovered optimal cellular unit cells exhibited 30–100% higher natural frequency and 300% higher energy absorption than those of the biomimetic counterparts. The discovered optimal unit cells were validated through experimental and simulation comparisons. The machine learning framework in this study would help in designing load carrying engineering structures with increased natural frequency and enhanced energy absorption capability.more » « less
-
Abstract We introduce frequency propagation, a learning algorithm for nonlinear physical networks. In a resistive electrical circuit with variable resistors, an activation current is applied at a set of input nodes at one frequency and an error current is applied at a set of output nodes at another frequency. The voltage response of the circuit to these boundary currents is the superposition of an activation signal and an error signal whose coefficients can be read in different frequencies of the frequency domain. Each conductance is updated proportionally to the product of the two coefficients. The learning rule is local and proved to perform gradient descent on a loss function. We argue that frequency propagation is an instance of a multimechanism learning strategy for physical networks, be it resistive, elastic, or flow networks. Multimechanism learning strategies incorporate at least two physical quantities, potentially governed by independent physical mechanisms, to act as activation and error signals in the training process. Locally available information about these two signals is then used to update the trainable parameters to perform gradient descent. We demonstrate how earlier work implementing learning via chemical signaling in flow networks (Anisetti, Scellier, et al., 2023) also falls under the rubric of multimechanism learning.more » « less
-
Deep neural networks (DNNs) have showcased their remarkable precision in approximating smooth functions. However, they suffer from the spectral bias, wherein DNNs typically exhibit a tendency to prioritize the learning of lower-frequency components of a function, struggling to effectively capture its high-frequency features. This paper is to address this issue. Notice that a function having only low frequency components may be well-represented by a shallow neural network (SNN), a network having only a few layers. By observing that composition of low frequency functions can effectively approximate a high-frequency function, we propose to learn a function containing high-frequency components by composing several SNNs, each of which learns certain low-frequency information from the given data. We implement the proposed idea by exploiting the multi-grade deep learning (MGDL) model, a recently introduced model that trains a DNN incrementally, grade by grade, a current grade learning from the residue of the previous grade only an SNN (with trainable parameters) composed with the SNNs (with fixed parameters) trained in the preceding grades as features. We apply MGDL to synthetic, manifold, colored images, and MNIST datasets, all characterized by presence of high-frequency features. Our study reveals that MGDL excels at representing functions containing high-frequency information. Specifically, the neural networks learned in each grade adeptly capture some low-frequency information, allowing their compositions with SNNs learned in the previous grades effectively representing the high-frequency features. Our experimental results underscore the efficacy of MGDL in addressing the spectral bias inherent in DNNs. By leveraging MGDL, we offer insights into overcoming spectral bias limitation of DNNs, thereby enhancing the performance and applicability of deep learning models in tasks requiring the representation of high-frequency information. This study confirms that the proposed method offers a promising solution to address the spectral bias of DNNs. The code is available on GitHub: Addressing Spectral Bias via MGDL.more » « less
-
We study the problem of imitation learning via inverse reinforcement learning where the agent attempts to learn an expert's policy from a dataset of collected state, action tuples. We derive a new Robust model-based Offline Imitation Learning method (ROIL) that mitigates covariate shift by avoiding estimating the expert's occupancy frequency. Frequently in offline settings, there is insufficient data to reliably estimate the expert's occupancy frequency and this leads to models that do not generalize well. Our proposed approach, ROIL, is a method that is guaranteed to recover the expert's occupancy frequency and is efficiently solvable as an LP. We demonstrate ROIL's ability to achieve minimal regret in large environments under covariate shift, such as when the state visitation frequency of the demonstrations does not come from the expert.more » « less
