Technology Category
Machine Learning: Deep Neural Architectures and Foundation ModelsCognitive Modeling & Cognitive Systems: Neural Spike CodingIntelligent Robots: Embodied AI
Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures
🤖 AI Summary
Artificial neural networks (ANNs) lack biological interpretability in architectural design. Method: Inspired by the bilaterally symmetric nervous system of planarians—featuring a primitive brain region and dual longitudinal nerve cords organized in a branch-and-integrate topology—we propose a biologically plausible ANN architecture. This design integrates modular dual-path branching, cross-path dynamic feature fusion, and co-optimized training into the ResNet framework, systematically incorporating neuroevolutionary principles from early bilaterians. Contribution/Results: Evaluated on CIFAR-10 and CIFAR-100 image classification, our model significantly outperforms baseline ResNet in accuracy, demonstrating that neuroanatomically grounded design enhances ANN generalization and performance. This work establishes a novel, interpretable, and scalable paradigm for brain-inspired intelligence.
Technology Category
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Brain-inspired computing
Flatworm neural network
Image recognition accuracy
Innovation
Methods, ideas, or system contributions that make the work stand out.
Flatworm-inspired Neural Network
ResNet Model Improvement
Image Recognition Accuracy
🔎 Similar Papers
No similar papers found.
