Supervised Training Rapidly Degrades Early Visual

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

Derived from arXiv:2605.30556 - Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules

## Core Concept
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 ...

## Key Insights
- Derived from arXiv:2605.30556
- Published: 2026-05-28
- Utility Score: 0.97
- Authors: Nils Leutenegger

## Activation
supervised-training-rapidly-degrades-early-visual, 2605.30556

## References
- arXiv: https://arxiv.org/abs/2605.30556