Deep neural networks and image classification in biological vision.
Deep neural networks and image classification in biological vision.
复制标题
生物视觉中的深度神经网络和图像分类。
DOI：
10.1016/j.visres.2022.108058
复制
发表时间：
2022
期刊：
影响因子：
1.8
通讯作者：
Charles Leek E
中科院分区：
文献类型：
--
作者：
Charles Leek E
在本文中，我们考虑了使用深度卷积神经网络来理解生物视觉的最新进展。我们重点关注关于前馈深度卷积神经网络 (fDCNN) 作为生物系统中图像分类模型的合理性的主张。尽管这些网络与生物视觉系统的某些特性具有相似性，并且某些 fDCNN 具有显着的性能准确性，但我们认为它们作为理解图像分类的框架的合理性仍不清楚。我们强调了我们认为与评估用于检查生物视觉的任何形式的 DNN 相关的两个关键问题：(1) 分析中的网络透明度——即理解网络做什么以及如何做的挑战。 (2) 使用定量和定性性能测量来确定比较网络性能和生物系统的适当基准。我们表明，fDCNN 和生物视觉之间存在重要差异，反映了计算架构和表示结构的根本差异，支持这些网络和生物系统中的图像分类。
In this paper we consider recent advances in the use of deep convolutional neural networks to understanding biological vision. We focus on claims about the plausibility of feedforward deep convolutional neural networks (fDCNNs) as models of image classification in the biological system. Despite the putative similarity of these networks to some properties of the biological vision system, and the remarkable levels of performance accuracy of some fDCNNs, we argue that their plausibility as a framework for understanding image classification remains unclear. We highlight two key issues that we suggest are relevant to the evaluation of any form of DNN used to examine biological vision: (1) Network transparency under analysis – that is, the challenge of understanding what networks do, and how they do it. (2) Identifying appropriate benchmarks for comparing network performance and the biological system using both quantitative and qualitative performance measures. We show that there are important divergences between fDCNNs and biological vision that reflect fundamental differences in computational architectures, and representational structures, supporting image classification in these networks and the biological system.