The evaluation resolution has been shown to have a significant impact on the identification of the "learning rule" that exhibits the most brain-like characteristics at V1. [R]

Excerpt

The preprint can be accessed via the following link: https://arxiv.org/abs/2608.12408 (q-bio.NC / cs.LG). And for the code: https://github.com/nilsleut/evaluation-resolution-rsa The following assertion is frequently made in model-brain comparisons: untrained convolutional neural networks (CNNs) have the capacity to match or surpass backpropagation-trained CNNs at the early visual cortex (V1) in recurrent self-attention (RSA). The present study demonstrates that this phenomenon is predominantly a