Cognition-Based Deep Learning: Progresses and Perspectives - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Cognition-Based Deep Learning: Progresses and Perspectives

(1) , (1) , (1) , (1) , (1)
1
Kai Yi
  • Function : Author
  • PersonId : 1033455
Shitao Chen
  • Function : Author
  • PersonId : 1033456
Yu Chen
  • Function : Author
  • PersonId : 1033457
Chao Xia
  • Function : Author
  • PersonId : 1033458
Nanning Zheng
  • Function : Author
  • PersonId : 1033459

Abstract

The human brain is composed of multiple modular subsystems, with a unique way interacting among each other. These subsystems have their own unique characteristics and interact to support cognitive functions such as memory, attention and cognitive control. Nowadays, deep learning methods based on the above-mentioned functions accompanied with knowledge are widely used to design more dynamic, robust and powerful systems. We first review and summarize the progresses of cognition-based deep neural networks, and how cognitive mechanisms can be applied to more brain-like neural networks. Then we propose a general framework for the design of cognition-based deep learning system. Although great efforts have been made in this field, cognition-based deep learning is still in its early age. We put forward the potential directions towards this field, such as associative memory in deep learning, interpretable network with cognitive mechanisms, and deep reinforcement learning based on cognitive science.
Fichier principal
Vignette du fichier
467708_1_En_11_Chapter.pdf (137.48 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01821031 , version 1 (22-06-2018)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Kai Yi, Shitao Chen, Yu Chen, Chao Xia, Nanning Zheng. Cognition-Based Deep Learning: Progresses and Perspectives. 14th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2018, Rhodes, Greece. pp.121-132, ⟨10.1007/978-3-319-92007-8_11⟩. ⟨hal-01821031⟩
306 View
93 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More