Interpretability of artificial neural network models in artificial intelligence versus neuroscience

被引：24

作者：

Kar, Kohitij ^{[1
,2
,3
,4
]}

Kornblith, Simon ^{[5
]}

Fedorenko, Evelina ^{[2
,3
]}

机构：

[1] York Univ, Ctr Vis Res, Dept Biol, Toronto, ON, Canada

[2] MIT, McGovern Inst Brain Res, Cambridge, MA 02139 USA

[3] MIT, Dept Brain & Cognit Sci, Cambridge, MA 02139 USA

[4] MIT, Ctr Brains Minds & Machines, Cambridge, MA 02139 USA

[5] Brain Team, Google Res, Toronto, ON, Canada

来源：

NATURE MACHINE INTELLIGENCE | 2022年 / 4卷 / 12期

关键词：

D O I：

10.1038/s42256-022-00592-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The notion of 'interpretability' of artificial neural networks (ANNs) is of growing importance in neuroscience and artificial intelligence (AI). But interpretability means different things to neuroscientists as opposed to AI researchers. In this article, we discuss the potential synergies and tensions between these two communities in interpreting ANNs.

引用

页码：1065 / 1067

页数：3

共 50 条

[21] Classical versus artificial neural network analysis
Newey, VR
ULTRASOUND IN OBSTETRICS & GYNECOLOGY, 1997, 10 (01) : 5 - 8
[22] Artificial Neural Network versus Linear Models Forecasting Doha Stock Market
Yousif, Adil
Elfaki, Faiz
4TH INTERNATIONAL CONFERENCE ON MATHEMATICAL APPLICATIONS IN ENGINEERING 2017 (ICMAE'17), 2018, 949
[23] Predicting shrimp growth: Artificial neural network versus nonlinear regression models
Yu, R
Leung, P
Bienfang, P
AQUACULTURAL ENGINEERING, 2006, 34 (01) : 26 - 32
[24] Artificial intelligence in virtual screening: Models versus experiments
Murugan, N. Arul
Priya, Gnana Ruba
Sastry, G. Narahari
Markidis, Stefano
DRUG DISCOVERY TODAY, 2022, 27 (07) : 1913 - 1923
[25] Artificial intelligence neural network based on intelligent diagnosis
Xiren Li
Journal of Ambient Intelligence and Humanized Computing, 2021, 12 : 923 - 931
[26] Artificial intelligence neural network based on intelligent diagnosis
Li, Xiren
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 12 (01) : 923 - 931
[27] Artificial Intelligence Detection of Cervical Spine Fractures Using Convolutional Neural Network Models
Liawrungrueang, Wongthawat
Han, Inbo
Cholamjiak, Watcharaporn
Sarasombath, Peem
Riew, K. Daniel
NEUROSPINE, 2024, 21 (03) : 833 - 841
[28] Using emotional intelligence to predict job stress: Artificial neural network and regression models
Allahyari, Elahe
Gholami, Abdollah
Arab-Zozani, Morteza
Ameri, Hosein
Nasseh, Negin
JOURNAL OF HEALTH AND SAFETY AT WORK, 2021, 11 (03) : 516 - 528
[29] Research on neural network algorithm in artificial intelligence recognition
Li, Yihong
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS, 2022, 53
[30] Prototypes and portability in artificial neural network models
Shultz, TR
BEHAVIORAL AND BRAIN SCIENCES, 2000, 23 (04) : 493 - +

← 1 2 3 4 5 →