Pattern memory cannot be completely and truly realized in deep neural networks
Abstract The unknown boundary issue, between superior computational capability of deep neural networks (DNNs) and human cognitive ability, has becoming crucial and foundational theoretical problem in AI evolution. Undoubtedly, DNN-empowered AI capability is increasingly surpassing human intelligence...
Saved in:
Main Authors: | Tingting Li, Ruimin Lyu, Zhenping Xie |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-80647-0 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Yours Truly /
by: Greenwood, Kirsty, 1982-
Published: (2012) -
Optimal Variational Method for Truly Nonlinear Oscillators
by: Vasile Marinca, et al.
Published: (2013-01-01) -
Deep Blue Cannot Play Checkers: The Need for Generalized Intelligence for Mobile Robots
by: Troy D. Kelley, et al.
Published: (2010-01-01) -
Peer-to-Peer Jini for Truly Service-Oriented WSNs
by: António Pereira, et al.
Published: (2011-05-01) -
Implementation of Genetic Algorithm Integrated with the Deep Neural Network for Estimating at Completion Simulation
by: Karrar Raoof Kareem Kamoona, et al.
Published: (2019-01-01)