The brains of all bilaterally symmetric animals on Earth are divided into left and right hemispheres. The anatomy and functionality of the hemispheres have a large degree of overlap, but there are asymmetries and they specialise to possess different attributes. Other authors have used computational models to mimic hemispheric asymmetries with a focus on reproducing human data on semantic and visual processing tasks. We took a different approach and aimed to understand how dual hemispheres in a bilateral architecture interact to perform well in a given task. We propose a bilateral artificial neural network that imitates lateralisation observed in nature: that the left hemisphere specialises in specificity and the right in generality. We used different training objectives to achieve the desired specialisation and tested it on an image classification task with two different CNN backbones -- ResNet and VGG. Our analysis found that the hemispheres represent complementary features that are exploited by a network head which implements a type of weighted attention. The bilateral architecture outperformed a range of baselines of similar representational capacity that don't exploit differential specialisation, with the exception of a conventional ensemble of unilateral networks trained on a dual training objective for specifics and generalities. The results demonstrate the efficacy of bilateralism, contribute to the discussion of bilateralism in biological brains and the principle may serves as an inductive bias for new AI systems.

翻译：地球上所有两侧对称动物的大脑均分为左右半球。两个半球的解剖结构和功能虽高度重叠，但存在非对称性并各自发展出不同特性。已有研究者通过计算模型模拟半球非对称性，重点复现人类在语义和视觉处理任务中的数据表现。我们采用不同路径，旨在理解双侧架构中双半球如何协同以出色完成特定任务。我们提出一种模仿自然界偏侧化现象的双侧人工神经网络：左半球专精于特异性，右半球专精于普遍性。通过不同训练目标实现所需特异性，并在基于ResNet和VGG两种CNN骨干网络的图像分类任务中进行测试。分析发现，双半球能表征互补特征，这些特征由实现加权注意力机制的网络头部加以利用。该双侧架构在类似表征能力、未采用差异化特化的基线模型中表现最优，但不及采用双重训练目标（同时追求特化与泛化）的传统单侧网络集成方案。实验证明了双侧机制的有效性，为生物大脑的双侧性讨论提供新见解，且该原理可作为新型AI系统的归纳偏置。