paper-with-me

홈 › Papers

Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures

2025-01-08 · Ziyuan Huang, Mark Newman, Maria Vaida, Srikar Bellur, Roozbeh Sadeghian, Andrew Siu, Hui Wang, Kevin Huggins

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.

📄 PDF Abstract BibTeX arXiv:2501.04700

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

Non-bilaterians as Model Systems for Tissue Mechanics

2023-06-02 · Setareh Gooshvar, Gopika Madhu, Melissa Ruszczyk, Vivek N. Prakash

In animals, epithelial tissues are barriers against the external environment, providing protection against biological, chemical, and physical damage. Depending on the animal's physiology and behavior, these tissues encou…

model

Advancing 3D Medical Image Segmentation: Unleashing the Potential of Planarian Neural Networks in Artificial Intelligence

2025-05-07 · Ziyuan Huang, Kevin Huggins, Srikar Bellur

Our study presents PNN-UNet as a method for constructing deep neural networks that replicate the planarian neural network (PNN) structure in the context of 3D medical image data. Planarians typically have a cerebral stru…

Data AugmentationHippocampusImage SegmentationMedical Image Segmentation+1

Recombinant transfer in the basic genome of E. coli

2015-07-14

An approximation to the ~4 Mbp basic genome shared by 32 strains of E. coli representing six evolutionary groups has been derived and analyzed computationally. A multiple-alignment of the 32 complete genome sequences was…

Registering the evolutionary history in individual-based models of speciation

2017-12-19

Understanding the emergence of biodiversity patterns in nature is a central problem in biology. Theoretical models of speciation have addressed this question in the macroecological scale, but little has been investigated…

Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination

2019-06-18 · Shauharda Khadka, Somdeb Majumdar, Santiago Miret, Stephen Mcaleer 외

Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely o…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)