Deep Feedback Models

• URL: http://arxiv.org/abs/2509.15905v1
• Date: Fri, 19 Sep 2025 12:03:18 GMT
• Title: Deep Feedback Models
• Authors: David Calhas, Arlindo L. Oliveira,
• Abstract summary: Deep Feedback Models (DFMs) are a new class of stateful neural networks that combine bottom up input with high level representations over time.<n>This feedback mechanism introduces dynamics into otherwise static architectures, enabling DFMs to iteratively refine their internal state.<n>We measure DFMs under two key conditions: robustness to noise and generalization with limited data.
• Score: 0.9310318514564272
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Feedback Models (DFMs) are a new class of stateful neural networks that combine bottom up input with high level representations over time. This feedback mechanism introduces dynamics into otherwise static architectures, enabling DFMs to iteratively refine their internal state and mimic aspects of biological decision making. We model this process as a differential equation solved through a recurrent neural network, stabilized via exponential decay to ensure convergence. To evaluate their effectiveness, we measure DFMs under two key conditions: robustness to noise and generalization with limited data. In both object recognition and segmentation tasks, DFMs consistently outperform their feedforward counterparts, particularly in low data or high noise regimes. In addition, DFMs translate to medical imaging settings, while being robust against various types of noise corruption. These findings highlight the importance of feedback in achieving stable, robust, and generalizable learning. Code is available at https://github.com/DCalhas/deep_feedback_models.

Related papers

• Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification [8.837732238971187]
  Functional magnetic resonance imaging (fMRI) enables non-invasive brain disorder classification by capturing blood-oxygen-level-dependent (BOLD) signals.<n>Most existing methods rely on functional connectivity (FC) via Pearson correlation.<n>We benchmark state-of-the-art temporal models on raw BOLD signals across five public datasets.
  arXiv  Detail & Related papers  (2026-02-09T04:42:42Z)
• Deep Recurrence for Dynamical Segmentation Models [0.0]
  We propose a predictive coding inspired feedback mechanism that introduces a recurrent loop from output to input, allowing the model to refine its internal state over time.<n>We implement this mechanism within a standard U-Net architecture and introduce two biologically motivated operations, softmax projection and exponential decay, to ensure stability of the feedback loop.<n>We show that the feedback model significantly outperforms its feedforward counterpart in noisy conditions and generalizes more effectively with limited supervision.
  arXiv  Detail & Related papers  (2025-07-14T10:41:07Z)
• Data-Driven Reconstruction and Characterization of Stochastic Dynamics via Dynamical Mode Decomposition [0.0]
  Noise limits the performance and predictive capabilities of classical and quantum dynamical systems.<n>We introduce a general, data-driven framework based on Dynamical Mode Decomposition (DMD) to analyze system dynamics under noise.<n>This methodology provides a broadly applicable tool for diagnostic, predictive, noise mitigation analyses, and control in complex systems.
  arXiv  Detail & Related papers  (2025-07-08T08:59:06Z)
• FEMSN: Frequency-Enhanced Multiscale Network for fault diagnosis of rotating machinery under strong noise environments [0.6970521089724208]
  Rolling bearings are critical components of rotating machinery, and their proper functioning is essential for industrial production.<n>Existing condition monitoring methods focus on extracting discnative features from time-domain signals to assess bearing health status.<n>This paper proposes a novel CNN-based model named FEMSN to learn distinctive fault-related features in such scenarios.
  arXiv  Detail & Related papers  (2025-05-07T07:58:48Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising [33.383511185170214]
  Fluorescence Micrograph to Self (FM2S) is a zero-shot denoiser that achieves efficient Fluorescence Micrograph to Self (FM2S) denoising through three key innovations.<n>Experiments across FMI datasets demonstrate FM2S's superiority: It outperforms CVF-SID by 1.4dB PSNR on average while requiring 0.1% parameters of AP-BSN.
  arXiv  Detail & Related papers  (2024-12-13T10:45:25Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Diffusion Recommender Model [85.9640416600725]
  We propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner.<n>To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis.
  arXiv  Detail & Related papers  (2023-04-11T04:31:00Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• The role of noise in denoising models for anomaly detection in medical images [62.0532151156057]
  Pathological brain lesions exhibit diverse appearance in brain images. Unsupervised anomaly detection approaches have been proposed using only normal data for training. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes.
  arXiv  Detail & Related papers  (2023-01-19T21:39:38Z)
• Establishment of Neural Networks Robust to Label Noise [0.0]
  In this paper, we have examined the fundamental concept underlying related label noise approaches. A transition matrix estimator has been created, and its effectiveness against the actual transition matrix has been demonstrated. We are not efficiently able to demonstrate the influence of the transition matrix noise correction on robustness enhancements due to our inability to correctly tune the complex convolutional neural network model.
  arXiv  Detail & Related papers  (2022-11-28T13:07:23Z)
• On the benefits of robust models in modulation recognition [53.391095789289736]
  Deep Neural Networks (DNNs) using convolutional layers are state-of-the-art in many tasks in communications. In other domains, like image classification, DNNs have been shown to be vulnerable to adversarial perturbations. We propose a novel framework to test the robustness of current state-of-the-art models.
  arXiv  Detail & Related papers  (2021-03-27T19:58:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.