TopoNets: High-Performing Vision and Language Models with Brain-Like Topography

Previously discussed at <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=42884338">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=42884338</a>

Please do not post this again - the paper is utter garbage, I think.<p>It is veiled to to making network topology matching the human brain the new goal, instead of, you know, the loss.