دورية أكاديمية

Meta-learning as a bridge between neural networks and symbolic Bayesian models.

التفاصيل البيبلوغرافية
العنوان: Meta-learning as a bridge between neural networks and symbolic Bayesian models.
المؤلفون: McCoy RT; Department of Linguistics, Yale University, New Haven, CT, USA tom.mccoy@yale.eduhttps://rtmccoy.com/., Griffiths TL; Departments of Psychology and Computer Science, Princeton University, Princeton, NJ, USA tomg@princeton.eduhttp://cocosci.princeton.edu/tom/.
المصدر: The Behavioral and brain sciences [Behav Brain Sci] 2024 Sep 23; Vol. 47, pp. e155. Date of Electronic Publication: 2024 Sep 23.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Cambridge Univ. Press Country of Publication: England NLM ID: 7808666 Publication Model: Electronic Cited Medium: Internet ISSN: 1469-1825 (Electronic) Linking ISSN: 0140525X NLM ISO Abbreviation: Behav Brain Sci Subsets: MEDLINE
أسماء مطبوعة: Original Publication: Cambridge [Eng.], New York, Cambridge Univ. Press.
مواضيع طبية MeSH: Bayes Theorem* , Neural Networks, Computer* , Learning*/physiology, Humans
مستخلص: Meta-learning is even more broadly relevant to the study of inductive biases than Binz et al. suggest: Its implications go beyond the extensions to rational analysis that they discuss. One noteworthy example is that meta-learning can act as a bridge between the vector representations of neural networks and the symbolic hypothesis spaces used in many Bayesian models.
تواريخ الأحداث: Date Created: 20240923 Date Completed: 20240923 Latest Revision: 20240923
رمز التحديث: 20240923
DOI: 10.1017/S0140525X24000116
PMID: 39311528
قاعدة البيانات: MEDLINE
الوصف
تدمد:1469-1825
DOI:10.1017/S0140525X24000116