Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules
CORRECTION (August 2026): the central finding of this paper is not supported. An evaluation-mode defect left the batch-normalisation layers of the predictive-coding and STDP conditions in training mode during feature extraction, producing their apparent preservation of V1 alignment. With the defect repaired, predictive coding degrades V1 alignment more than backpropagation does, not less. The finding that training degrades V1 alignment for every rule tested does survive. See the correction note on page 1; the original abstract below and the body are unchanged from v1. Corrected analysis: arXiv:2608.12408. 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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Forgetting of task-specific knowledge in model merging-based continual learning
This paper investigates the linear merging of models in the context of continual learning (CL). Using controlled visual cues in computer vision experiments, we demonstrate that merging largely preserves or enhances share…
Continual LearningOn the Geometry of On-Policy Distillation
On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of OPD updates in parameter space and compar…
Reinforcement LearningAn Efficient Self-Supervised Cross-View Training For Sentence Embedding
Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language…
Contrastive LearningLanguage ModelingLanguage ModellingRepresentation Learning+5Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabili…
Reinforcement LearningCan semi-supervised learning reduce the amount of manual labelling required for effective radio galaxy morphology classification?
In this work, we examine the robustness of state-of-the-art semi-supervised learning (SSL) algorithms when applied to morphological classification in modern radio astronomy. We test whether SSL can achieve performance co…
AstronomyMorphology classification