Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules

• URL: http://arxiv.org/abs/2605.30556v1
• Date: Thu, 28 May 2026 20:39:52 GMT
• Title: Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules
• Abstract summary: Random, untrained neural networks consistently match or exceed trained networks in representational similarity to early visual cortex.<n>We investigate it by tracking representational similarity analysis (RSA) alignment to human fMRI data across training for four learning rules.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Random, untrained neural networks consistently match or exceed trained networks in representational similarity to early visual cortex. This puzzling finding challenges the assumption that learning improves brain alignment. We investigate it by tracking representational similarity analysis (RSA) alignment to human fMRI data across training for four learning rules: backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP). Using 720 object images from the THINGS database and fMRI data from three subjects across six visual ROIs, we measure Spearman correlations between model and brain representational dissimilarity matrices at eight training checkpoints (epochs 0-40). We find that (1) a single epoch of training reduces V1 alignment by 25-90%, depending on the learning rule; (2) backpropagation reduces V1 alignment most severely (delta r = -0.080), while predictive coding and STDP preserve substantially more (delta r ~ -0.04); and (3) a weaker, opposite tendency appears in object-selective cortex (LOC), where BP shows the largest increase in alignment during training, although the absolute change is small. These results suggest that untrained architectures capture low-level visual statistics through inductive biases alone, and that global error signals (BP) reshape early representations more aggressively than local learning rules (PC, STDP), which better preserve brain-like structure.

Related papers

• Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex [0.0]
  We find that a common result in this setting, that untrained or locally trained networks rival or beat backpropagation at early visual cortex, depends strongly on the resolution at which the network is evaluated.<n>Four candidate mechanisms are tested and none accounts for it: train/eval resolution matching, low-level Gabor and pixel structure, the normalization state of the untrained baseline, and convergence of the pooled descriptor toward a global brightness statistic.
  arXiv  Detail & Related papers  (2026-08-11T15:50:58Z)
• Experimental Analysis of Neural Network-Based Image Classification on the CIFAR-10 Dataset [0.0]
  An experimental investigation of neural image classification on the CIFAR-10 benchmark is presented through fully connected and convolutional network formulations.<n>The analysis emphasizes the complete learning pipeline: image vectorization, normalization, one-hot class encoding, supervised loss minimization, learning-rate selection, mini-batch training, convolutional feature extraction, max-pooling, and validation-based assessment.
  arXiv  Detail & Related papers  (2026-06-17T00:35:27Z)
• An extremely coarse feedback signal is sufficient for learning human-aligned visual representations [2.9506547907696006]
  We investigate how the coarseness of a learning signal shapes representational alignment with human vision.<n>We train hundreds of neural networks across convolutional and transformer architectures on these coarse classification tasks.<n>We find that networks trained to distinguish as few as 8 broad categories learn representations that match or exceed the neural alignment of models distinguishing 1,000-classes.
  arXiv  Detail & Related papers  (2026-05-07T01:02:21Z)
• UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces [7.71021447675552]
  Existing approaches face critical challenges, including limited-scale heterogeneous data, cross-domain distribution shift, and fewer trainable neural signals.<n>In this work, we propose a unified pre-trained model for invasive Brain Interfaces.<n>Results suggest that UniBCI provides a practical step toward general-purpose neural foundation models.
  arXiv  Detail & Related papers  (2026-04-30T06:30:24Z)
• Untrained CNNs Match Backpropagation at V1: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI [0.0]
  We compare four learning rules -- backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP) -- applied to identical convolutional architectures.<n>We find that early visual alignment is primarily architecture-driven, while supervised objectives drive late alignment.
  arXiv  Detail & Related papers  (2026-04-18T06:53:35Z)
• Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts [1.9458156037869137]
  convergent learning is the degree to which neural systems arrive at similar internal representations.<n>We present a large-scale audit of convergent learning spanning dozens of vision models and thousands of layer-pair comparisons.<n>Findings fill critical gaps in our understanding of representational convergence, with implications for neuroscience and AI.
  arXiv  Detail & Related papers  (2025-02-26T00:04:24Z)
• 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)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections [10.188771327458651]
  Spike-timing-dependent plasticity (STDP) is a general learning rule in the brain, but spiking neural networks (SNNs) trained with STDP alone is inefficient and perform poorly. We design an adaptive synaptic filter and introduce the adaptive spiking threshold to enrich the representation ability of SNNs. Our model achieves the current state-of-the-art performance of unsupervised STDP-based SNNs in the MNIST and FashionMNIST datasets.
  arXiv  Detail & Related papers  (2022-07-06T14:53:32Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)
• A Simple Framework for Contrastive Learning of Visual Representations [116.37752766922407]
  This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We show that composition of data augmentations plays a critical role in defining effective predictive tasks. We are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet.
  arXiv  Detail & Related papers  (2020-02-13T18:50:45Z)

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.