On the hazards of relating representations and inductive biases

被引：0

作者：

Quilty-Dunn, Jake ^{[1
]}

Porot, Nicolas ^{[2
]}

Mandelbaum, Eric ^{[3
,4
,5
]}

机构：

[1] Washington Univ, Dept Philosophy, Philosophy Neurosci Psychol Program, St Louis, MO 63130 USA

[2] Mohammed VI Polytech Univ, Africa Inst Res Econ & Social Sci, Rabat, Morocco

[3] CUNY, Grad Ctr, Dept Philosophy, New York, NY USA

[4] CUNY, Grad Ctr, Dept Psychol, New York, NY USA

[5] CUNY, Baruch Coll, New York, NY USA

来源：

BEHAVIORAL AND BRAIN SCIENCES | 2023年 / 46卷

关键词：

MODELS;

D O I：

10.1017/S0140525X23002042

中图分类号：

B84 [心理学];

学科分类号：

04 ; 0402 ;

摘要：

The success of models of human behavior based on Bayesian inference over logical formulas or programs is taken as evidence that people employ a "language-of-thought" that has similarly discrete and compositional structure. We argue that this conclusion problematically crosses levels of analysis, identifying representations at the algorithmic level based on inductive biases at the computational level.

引用

页数：75

共 50 条

[41] Demystifying Inductive Biases for (Beta-)VAE Based Architectures
Zietlow, Dominik
Rolinek, Michal
Martius, Georg
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[42] Inductive Biases for Low Data VQA: A Data Augmentation Approach
Askarian, Narjes
Abbasnejad, Ehsan
Zukerman, Ingrid
Buntine, Wray
Haffari, Gholamreza
2022 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2022), 2022, : 231 - 240
[43] ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
d'Ascoli, Stephane
Touvron, Hugo
Leavitt, Matthew L.
Morcos, Ari S.
Biroli, Giulio
Sagun, Levent
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[44] Theoretical and empirical evidence for the impact of inductive biases on cultural evolution
Griffiths, Thomas L.
Kalish, Michael L.
Lewandowsky, Stephan
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES, 2008, 363 (1509) : 3503 - 3514
[45] Toward Out-of-Distribution Generalization Through Inductive Biases
Moruzzi, Caterina
PHILOSOPHY AND THEORY OF ARTIFICIAL INTELLIGENCE 2021, 2022, 63 : 57 - 66
[46] A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
Harrison, James
Metz, Luke
Sohl-Dickstein, Jascha
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[47] Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
Si, Chenglei
Friedman, Dan
Joshi, Nitish
Feng, Shi
Chen, Danqi
He, He
PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023): LONG PAPERS, VOL 1, 2023, : 11289 - 11310
[48] ConViT: improving vision transformers with soft convolutional inductive biases
d'Ascoli, Stephane
Touvron, Hugo
Leavitt, Matthew L.
Morcos, Ari S.
Biroli, Giulio
Sagun, Levent
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2022, 2022 (11):
[49] Inductive biases for deep learning of higher-level cognition
Goyal, Anirudh
Bengio, Yoshua
PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2022, 478 (2266):
[50] Learning an Interpretable Model for Driver Behavior Prediction with Inductive Biases
Arbabi, Salar
Tavernini, Davide
Fallah, Saber
Bowden, Richard
2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 3940 - 3947

← 1 2 3 4 5 →