Cognitive Neural Architecture Search Reveals Hierarchical Entailment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910924552536064 |
|---|---|
| author | Kuhn, Lukas Saba-Sadiya, Sari Roig, Gemma |
| author_facet | Kuhn, Lukas Saba-Sadiya, Sari Roig, Gemma |
| contents | Recent research has suggested that the brain is more shallow than previously thought, challenging the traditionally assumed hierarchical structure of the ventral visual pathway. Here, we demonstrate that optimizing convolutional network architectures for brain-alignment via evolutionary neural architecture search results in models with clear representational hierarchies. Despite having random weights, the identified models achieve brain-alignment scores surpassing even those of pretrained classification models - as measured by both regression and representational similarity analysis. Furthermore, through traditional supervised training, architectures optimized for alignment with late ventral regions become competitive classification models. These findings suggest that hierarchical structure is a fundamental mechanism of primate visual processing. Finally, this work demonstrates the potential of neural architecture search as a framework for computational cognitive neuroscience research that could reduce the field's reliance on manually designed convolutional networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11141 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cognitive Neural Architecture Search Reveals Hierarchical Entailment Kuhn, Lukas Saba-Sadiya, Sari Roig, Gemma Neural and Evolutionary Computing Artificial Intelligence Quantitative Methods Recent research has suggested that the brain is more shallow than previously thought, challenging the traditionally assumed hierarchical structure of the ventral visual pathway. Here, we demonstrate that optimizing convolutional network architectures for brain-alignment via evolutionary neural architecture search results in models with clear representational hierarchies. Despite having random weights, the identified models achieve brain-alignment scores surpassing even those of pretrained classification models - as measured by both regression and representational similarity analysis. Furthermore, through traditional supervised training, architectures optimized for alignment with late ventral regions become competitive classification models. These findings suggest that hierarchical structure is a fundamental mechanism of primate visual processing. Finally, this work demonstrates the potential of neural architecture search as a framework for computational cognitive neuroscience research that could reduce the field's reliance on manually designed convolutional networks. |
| title | Cognitive Neural Architecture Search Reveals Hierarchical Entailment |
| topic | Neural and Evolutionary Computing Artificial Intelligence Quantitative Methods |
| url | https://arxiv.org/abs/2502.11141 |