Deep Feedback Models

David Calhas, Arlindo L. Oliveira
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:4861-4869, 2026.

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 github.com/DCalhas/deep\emph{feedback}models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-calhas26a, title = { Deep Feedback Models }, author = {Calhas, David and Oliveira, Arlindo L.}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {4861--4869}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/calhas26a/calhas26a.pdf}, url = {https://proceedings.mlr.press/v300/calhas26a.html}, 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 github.com/DCalhas/deep\emph{feedback}models. } }
Endnote
%0 Conference Paper %T Deep Feedback Models %A David Calhas %A Arlindo L. Oliveira %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-calhas26a %I PMLR %P 4861--4869 %U https://proceedings.mlr.press/v300/calhas26a.html %V 300 %X 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 github.com/DCalhas/deep\emph{feedback}models.
APA
Calhas, D. & Oliveira, A.L.. (2026). Deep Feedback Models . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:4861-4869 Available from https://proceedings.mlr.press/v300/calhas26a.html.

Related Material