Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks

• URL: http://arxiv.org/abs/2605.08564v1
• Date: Fri, 08 May 2026 23:54:48 GMT
• Title: Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks
• Abstract summary: We evaluate five learning algorithms including modified FA and standard BP, applied to the same convolutional architecture with the CIFAR-10 dataset.<n>Our results indicate that modified FA algorithms converge on internal representations that are structurally similar to those produced by backpropagation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The feedback alignment (FA) algorithm offers a biologically plausible alternative to backpropagation (BP) for training neural networks yet notably fails to scale to convolutional architectures. Modifications have been proposed to address this limitation, but at questionable cost to biological plausibility. In this paper, we evaluate five learning algorithms including modified FA and standard BP, applied to the same convolutional architecture with the CIFAR-10 dataset. We provide a tripartite comparative analysis focusing on biological plausibility, interpretability, and computational complexity. Our results indicate that modified FA algorithms converge on internal representations that are structurally similar to those produced by backpropagation. In particular, it appears the functional success of modified FA algorithms may be rooted in their ability to mimic the representational geometry of backpropagation, converging on similar representations despite relying on fundamentally different weight update mechanisms.

Related papers

• Structure-Guided Adaptive Propagation for Protein-Protein Interaction Site Prediction [6.128739346306066]
  We present SGAP-PPIS, a structure-guided adaptive propagation model for PPIS prediction.<n>We show that SGAP-PPIS achieves competitive performance among the state-of-the-art methods on Test_60.
  arXiv  Detail & Related papers  (2026-06-01T07:03:00Z)
• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration [59.062085785106234]
  This article presents a general Bayesian learning framework for multi-modal groupwise image registration.<n>We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables.<n>Experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images.
  arXiv  Detail & Related papers  (2024-01-04T08:46:39Z)
• Unlocking the Potential of Similarity Matching: Scalability, Supervision and Pre-training [9.160910754837754]
  Backpropagation (BP) algorithm exhibits limitations in terms of biological plausibility, computational cost, and suitability for online learning. This study focuses on the primarily unsupervised similarity matching (SM) framework, which aligns with observed mechanisms in biological systems.
  arXiv  Detail & Related papers  (2023-08-02T20:34:55Z)
• Incorporating Prior Knowledge in Deep Learning Models via Pathway Activity Autoencoders [5.950889585409067]
  We propose a novel prior-knowledge-based deep auto-encoding framework, PAAE, for RNA-seq data in cancer. We show that, despite having access to a smaller set of features, our PAAE and PAVAE models achieve better out-of-set reconstruction results compared to common methodologies.
  arXiv  Detail & Related papers  (2023-06-09T11:12:55Z)
• Learning with augmented target information: An alternative theory of Feedback Alignment [0.0]
  We propose a novel theory of how Feedback Alignment (FA) works through the lens of information theory. FA learns effective representations by embedding target information into neural networks to be trained. We show this through the analysis of FA dynamics in idealized settings and then via a series of experiments.
  arXiv  Detail & Related papers  (2023-04-03T22:44:03Z)
• The Predictive Forward-Forward Algorithm [79.07468367923619]
  We propose the predictive forward-forward (PFF) algorithm for conducting credit assignment in neural systems. We design a novel, dynamic recurrent neural system that learns a directed generative circuit jointly and simultaneously with a representation circuit. PFF efficiently learns to propagate learning signals and updates synapses with forward passes only.
  arXiv  Detail & Related papers  (2023-01-04T05:34:48Z)
• A Robust Backpropagation-Free Framework for Images [47.97322346441165]
  We present an error kernel driven activation alignment algorithm for image data. EKDAA accomplishes through the introduction of locally derived error transmission kernels and error maps. Results are presented for an EKDAA trained CNN that employs a non-differentiable activation function.
  arXiv  Detail & Related papers  (2022-06-03T21:14:10Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)
• Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms [71.62575565990502]
  We prove that the generalization error of an optimization algorithm can be bounded on the complexity' of the fractal structure that underlies its generalization measure. We further specialize our results to specific problems (e.g., linear/logistic regression, one hidden/layered neural networks) and algorithms.
  arXiv  Detail & Related papers  (2021-06-09T08:05:36Z)
• Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows [7.119831726757417]
  We propose a new type of VBPI, VBPI-NF, as a first step to empower phylogenetic posterior estimation with deep learning techniques. VBPI-NF uses normalizing flows to provide a rich family of flexible branch length distributions that generalize across different tree topologies.
  arXiv  Detail & Related papers  (2020-12-01T13:10:00Z)
• Investigating the Scalability and Biological Plausibility of the Activation Relaxation Algorithm [62.997667081978825]
  Activation Relaxation (AR) algorithm provides a simple and robust approach for approximating the backpropagation of error algorithm. We show that the algorithm can be further simplified and made more biologically plausible by introducing a learnable set of backwards weights. We also investigate whether another biologically implausible assumption of the original AR algorithm -- the frozen feedforward pass -- can be relaxed without damaging performance.
  arXiv  Detail & Related papers  (2020-10-13T08:02:38Z)

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.