Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures
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_ | 1866912180452982784 |
|---|---|
| author | Huang, Ziyuan Newman, Mark Vaida, Maria Bellur, Srikar Sadeghian, Roozbeh Siu, Andrew Wang, Hui Huggins, Kevin |
| author_facet | Huang, Ziyuan Newman, Mark Vaida, Maria Bellur, Srikar Sadeghian, Roozbeh Siu, Andrew Wang, Hui Huggins, Kevin |
| contents | This study examined the viability of enhancing the prediction accuracy of artificial neural networks (ANNs) in image classification tasks by developing ANNs with evolution patterns similar to those of biological neural networks. ResNet is a widely used family of neural networks with both deep and wide variants; therefore, it was selected as the base model for our investigation. The aim of this study is to improve the image classification performance of ANNs via a novel approach inspired by the biological nervous system architecture of planarians, which comprises a brain and two nerve cords. We believe that the unique neural architecture of planarians offers valuable insights into the performance enhancement of ANNs. The proposed planarian neural architecture-based neural network was evaluated on the CIFAR-10 and CIFAR-100 datasets. Our results indicate that the proposed method exhibits higher prediction accuracy than the baseline neural network models in image classification tasks. These findings demonstrate the significant potential of biologically inspired neural network architectures in improving the performance of ANNs in a wide range of applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04700 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures Huang, Ziyuan Newman, Mark Vaida, Maria Bellur, Srikar Sadeghian, Roozbeh Siu, Andrew Wang, Hui Huggins, Kevin Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 68T07 This study examined the viability of enhancing the prediction accuracy of artificial neural networks (ANNs) in image classification tasks by developing ANNs with evolution patterns similar to those of biological neural networks. ResNet is a widely used family of neural networks with both deep and wide variants; therefore, it was selected as the base model for our investigation. The aim of this study is to improve the image classification performance of ANNs via a novel approach inspired by the biological nervous system architecture of planarians, which comprises a brain and two nerve cords. We believe that the unique neural architecture of planarians offers valuable insights into the performance enhancement of ANNs. The proposed planarian neural architecture-based neural network was evaluated on the CIFAR-10 and CIFAR-100 datasets. Our results indicate that the proposed method exhibits higher prediction accuracy than the baseline neural network models in image classification tasks. These findings demonstrate the significant potential of biologically inspired neural network architectures in improving the performance of ANNs in a wide range of applications. |
| title | Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 68T07 |
| url | https://arxiv.org/abs/2501.04700 |