{"slug": "bidirectional-representational-alignment-between-biological-and-artificial", "title": "Bidirectional representational alignment between biological and artificial neural networks", "summary": "Researchers at the Center for Computational Neuroscience, Flatiron Institute, and New York University developed a computational framework integrating spectral regularization with bidirectional predictivity analyses, demonstrating that steering spectral geometry in self-supervised contrastive vision models increased reverse predictivity with modest reductions in forward predictivity, yielding a 55% relative improvement in bidirectional predictivity between biological and artificial neural networks.", "body_md": "arXiv:2608.18244v1 Announce Type: new\nAbstract: Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric: model representations predict neural responses much better than neural responses predict model representations. This asymmetry raises the question of whether representational geometry contributes to bidirectional representational alignment. We hypothesized that steering representational geometry during training can systematically influence bidirectional alignment. To test this hypothesis, we developed a computational framework that integrates spectral regularization with bidirectional predictivity analyses. As an initial demonstration, we evaluated our framework using self-supervised contrastive vision models. Steering the spectral geometry of the learned representations substantially increased reverse predictivity with modest reductions in forward predictivity, yielding a 55% relative improvement in bidirectional predictivity. These improvements were accompanied by reduced effective dimensionality and a reorganization of the shared representational subspace, within which forward and reverse predictivity became approximately symmetric at intermediate spectral exponents. Overall, these findings demonstrate that representational geometry can be systematically steered to modulate bidirectional representational alignment between biological and artificial neural networks.", "url": "https://wpnews.pro/news/bidirectional-representational-alignment-between-biological-and-artificial", "canonical_source": "https://arxiv.org/abs/2608.18244", "published_at": "2026-08-20 04:00:00+00:00", "updated_at": "2026-08-20 04:14:25.615613+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "neural-networks", "ai-research"], "entities": ["Center for Computational Neuroscience", "Flatiron Institute", "New York University"], "alternates": {"html": "https://wpnews.pro/news/bidirectional-representational-alignment-between-biological-and-artificial", "markdown": "https://wpnews.pro/news/bidirectional-representational-alignment-between-biological-and-artificial.md", "text": "https://wpnews.pro/news/bidirectional-representational-alignment-between-biological-and-artificial.txt", "jsonld": "https://wpnews.pro/news/bidirectional-representational-alignment-between-biological-and-artificial.jsonld"}}