Brain-like functional specialization emerges spontaneously in deep neural networks.

Brain-like functional specialization emerges spontaneously in deep neural networks.
复制标题

类脑功能特化在深度神经网络中自发出现。

DOI:
10.1126/sciadv.abl8913
复制
发表时间:
2022-03-18
期刊:
影响因子:
13.6
通讯作者:
Kanwisher N
Kanwisher N
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Dobs K;Martinez J;Kell AJE;Kanwisher N

文献摘要

参考文献

被引文献

相似文献

人脑包含多个区域,具有不同的、往往高度专业化的功能,从识别面孔到理解语言,再到思考他人的想法。然而,为什么大脑皮层一开始就表现出如此高度的功能特化,目前还不清楚。这里,我们考虑了使用人工神经网络的人脸感知的情况,以检验这样的假设,即人脸识别在大脑中的功能分离反映了对更广泛的人脸和其他视觉类别的视觉识别问题的计算优化。我们发现,针对对象识别训练的网络在人脸识别方面表现不佳,反之亦然,针对这两个任务进行优化的网络自发地将自己分离到针对人脸和对象的单独系统中。然后,我们展示了其他视觉类别不同程度的功能分离,揭示了一种普遍的优化趋势(没有内置的特定于任务的归纳偏见),从而导致机器的功能专门化,我们猜测,也会导致大脑的专门化。机器中自发的功能专门化为人脑中的领域专一性提供了一种计算解释。
The human brain contains multiple regions with distinct, often highly specialized functions, from recognizing faces to understanding language to thinking about what others are thinking. However, it remains unclear why the cortex exhibits this high degree of functional specialization in the first place. Here, we consider the case of face perception using artificial neural networks to test the hypothesis that functional segregation of face recognition in the brain reflects a computational optimization for the broader problem of visual recognition of faces and other visual categories. We find that networks trained on object recognition perform poorly on face recognition and vice versa and that networks optimized for both tasks spontaneously segregate themselves into separate systems for faces and objects. We then show functional segregation to varying degrees for other visual categories, revealing a widespread tendency for optimization (without built-in task-specific inductive biases) to lead to functional specialization in machines and, we conjecture, also brains. Spontaneous functional specialization in machines provides a computational explanation for domain specificity in the human brain.
DOI: 10.1146/annurev-neuro-070815-013934
发表时间: 2016-07-08
影响因子: 13.9
作者:
Freiwald W;Duchaine B;Yovel G
通讯作者: Yovel G
DOI: 10.1038/s41467-019-09239-1
发表时间: 2019-03-19
影响因子: 16.6
作者:
Dobs, Katharina;Isik, Leyla;Kanwisher, Nancy
通讯作者: Kanwisher, Nancy
DOI: 10.1207/s15516709cog1502_2
发表时间: 1991-04-01
期刊: COGNITIVE SCIENCE
影响因子: 2.5
作者:
JACOBS, RA;JORDAN, MI;BARTO, AG
通讯作者: BARTO, AG
DOI: 10.3389/fpsyg.2012.00245
发表时间: 2012
影响因子: 3.8
作者:
Kriegeskorte N;Mur M
通讯作者: Mur M
DOI: 10.1016/j.cognition.2016.03.005
发表时间: 2016-07-01
期刊: COGNITION
影响因子: 3.4
作者:
Fausey, Caitlin M.;Jayaraman, Swapnaa;Smith, Linda B.
通讯作者: Smith, Linda B.