Journal article icon

Journal article

A mathematical theory of semantic development in deep neural networks

Abstract:

An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: What are the theoretical principles governing the ability of neural networks to acquire, organize, and deploy abstract knowledge by integrating across many individual experiences? We address this question by mathematically analyzing the nonlinear dynamics of learning ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1073/pnas.1820226116

Authors


More by this author
Institution:
University of Oxford
Division:
Medical Sciences Division
Department:
Experimental Psychology
Department:
Unknown
Role:
Author
ORCID:
0000-0002-9831-8812
Publisher:
National Academy of Sciences Publisher's website
Journal:
Proceedings of the National Academy of Sciences Journal website
Volume:
116
Issue:
23
Pages:
11537-11546
Publication date:
2019-05-17
Acceptance date:
2019-04-09
DOI:
EISSN:
1091-6490
ISSN:
0027-8424
Pmid:
31101713
Language:
English
Keywords:
Pubs id:
pubs:999449
UUID:
uuid:675edddf-32b3-4830-b781-6b47e02a3a8c
Local pid:
pubs:999449
Source identifiers:
999449
Deposit date:
2019-07-04

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP