CASIA OpenIR  > 学术期刊  > International Journal of Automation and Computing
Why Deep Neural Nets Cannot Ever Match Biological Intelligence and What To Do About It?
Danko Nikolic1,2,3
Source PublicationInternational Journal of Automation and Computing
ISSN1476-8186
2017
Volume14Issue:5Pages:532-541
SubtypeIJAC-HIC-2016-12-315.pdf
AbstractThe recently introduced theory of practopoiesis offers an account on how adaptive intelligent systems are organized. According to that theory, biological agents adapt at three levels of organization and this structure applies also to our brains. This is referred to as tri-traversal theory of the organization of mind or for short, a T3-structure. To implement a similar T3-organization in an artificially intelligent agent, it is necessary to have multiple policies, as usually used as a concept in the theory of reinforcement learning. These policies have to form a hierarchy. We define adaptive practopoietic systems in terms of hierarchy of policies and calculate whether the total variety of behavior required by real-life conditions of an adult human can be satisfactorily accounted for by a traditional approach to artificial intelligence based on T2-agents, or whether a T3-agent is needed instead. We conclude that the complexity of real life can be dealt with appropriately only by a T3-agent. This means that the current approaches to artificial intelligence, such as deep architectures of neural networks, will not suffice with fixed network architectures. Rather, they will need to be equipped with intelligent mechanisms that rapidly alter the architectures of those networks.
KeywordArtificial intelligence neural networks strong artificial intelligence practopoiesis, machine learning.
DOI10.1007/s11633-017-1093-8
Citation statistics
Cited Times:3[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/42477
Collection学术期刊_International Journal of Automation and Computing
Affiliation1.DXC Technology, Frankfurt am Main, Germany
2.Frankfurt Institute for Advanced Studies (FIAS), Ruth-Moufang-Straße 1, D-60438 Frankfurt/M, Germany
3.Department of Psychology, Faculty of Humanities and Social Sciences, University of Zagreb, Croatia
Recommended Citation
GB/T 7714
Danko Nikolic. Why Deep Neural Nets Cannot Ever Match Biological Intelligence and What To Do About It?[J]. International Journal of Automation and Computing,2017,14(5):532-541.
APA Danko Nikolic.(2017).Why Deep Neural Nets Cannot Ever Match Biological Intelligence and What To Do About It?.International Journal of Automation and Computing,14(5),532-541.
MLA Danko Nikolic."Why Deep Neural Nets Cannot Ever Match Biological Intelligence and What To Do About It?".International Journal of Automation and Computing 14.5(2017):532-541.
Files in This Item: Download All
File Name/Size DocType Version Access License
IJAC-HIC-2016-12-315(349KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Danko Nikolic]'s Articles
Baidu academic
Similar articles in Baidu academic
[Danko Nikolic]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Danko Nikolic]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: IJAC-HIC-2016-12-315.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.