Full Text:   <468>

Suppl. Mater.: 

CLC number: TP18

On-line Access: 2020-04-21

Received: 2019-09-30

Revision Accepted: 2019-12-15

Crosschecked: 2019-12-23

Cited: 0

Clicked: 1603

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Lei Xu

https://orcid.org/0000-0002-2752-1573

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2020 Vol.21 No.4 P.558-562

http://doi.org/10.1631/FITEE.1900541


Learning deep IA bidirectional intelligence


Author(s):  Lei Xu

Affiliation(s):  Centre for Cognitive Machines and Computational Health (CMaCH), School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; more

Corresponding email(s):   lxu@cs.sjtu.edu.cn

Key Words:  Abstraction, Least mean square error reconstruction (Lmser), Cognition, Image thinking, Abstract thinking, Synthesis reasoning


Lei Xu. Learning deep IA bidirectional intelligence[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(4): 558-562.

@article{title="Learning deep IA bidirectional intelligence",
author="Lei Xu",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="21",
number="4",
pages="558-562",
year="2020",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1900541"
}

%0 Journal Article
%T Learning deep IA bidirectional intelligence
%A Lei Xu
%J Frontiers of Information Technology & Electronic Engineering
%V 21
%N 4
%P 558-562
%@ 2095-9184
%D 2020
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1900541

TY - JOUR
T1 - Learning deep IA bidirectional intelligence
A1 - Lei Xu
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 21
IS - 4
SP - 558
EP - 562
%@ 2095-9184
Y1 - 2020
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1900541


Abstract: 
There has been a framework sketched for learning deep bidirectional intelligence. The framework has an inbound that features two actions: one is the acquiring action, which gets inputs in appropriate patterns, and the other is A-S cognition, derived from the abbreviated form of words abstraction and self-organization, which abstracts input patterns into concepts that are labeled and understood by self-organizing parts involved in the concept into structural hierarchies. The top inner domain accommodates relations and a priori knowledge with the help of the A-I thinking action that is responsible for the accumulation-amalgamation and induction-inspiration. The framework also has an outbound that comes with two actions. One is called I-S reasoning, which makes inference and synthesis (I-S) and is responsible for performing various tasks including image thinking and problem solving, and the other is called the interacting action, which controls, communicates with, and inspects the environment. Based on this framework, we further discuss the possibilities of design intelligence through synthesis reasoning.

深度IA双向智能


徐雷1,2
1上海交通大学电子信息与电气工程学院认知机器和计算健康研究中心,中国上海市,200240
2张江国家实验室脑与智能科技研究院神经网络计算研究中心,中国上海市,201210

摘要:概述了一个深度双向智能框架。由底向上方向有两个行为,一是获取信息形成适当的模式表示,二是抽象-自组织认知,简记为“A-S认知”,将输入模式抽象为概念,由一个标签表示,并通过自组织学习以理解模式构成的层次表示。而顶层内域中的行为统称为“A-I思维”,包含积累、融合、归纳、和灵感等。由顶向下方向也有两个行为,一个简称“I-S推理”,进行推理和综合,执行各种形象思维和问题求解任务,另一个是与环境交互,执行控制、通讯和检验的任务。在这个双向智能框架基础上,探讨了进行综合推理的可能性。

关键词:抽象;最小均方误差重建自组织学习(Lmser);认知;形象思维;抽象思维;综合推理

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Ballard DH, 1987. Modular learning in neural networks. Proc 6th National Conf on Artificial Intelligence, p.279-284.

[2]Dayan P, Hinton GE, Neal RM, et al., 1995. The Helmholtz machine. Neur Comput, 7(5):889-904.

[3]Hinton GE, Salakhutdinov RR, 2006. Reducing the dimensionality of data with neural networks. Science, 313(5786):504-507.

[4]Hubel DH, Wiesel TN, 1962. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J Physiol, 160(1):106-154.

[5]Le QV, Ranzato M, Monga R, et al., 2011. Building high-level features using large scale unsupervised learning. https://arxiv.org/abs/1112.6209

[6]Pan Y, 1996. The synthesis reasonning. Patt Recogn Artif Intell, 9:201-208.

[7]Qian X, 1983. On thinking sciences. Chin J Nat, 8:566.

[8]Xu L, 1991. Least MSE reconstruction for self-organization: (II) further theoretical and experimental studies on one-layer nets. Proc IEEE Int Joint Conf on Neural Networks, p.2362-2367.

[9]Xu L, 1993. Least mean square error reconstruction principle for self-organizing neural-nets. Neur Netw, 6(5):627-648.

[10]Xu L, 1995. YING-YANG machines: a Bayesian-Kullback scheme for unified learning and new results on vector quantization. Proc Int Conf on Neural Information Processing, p.977-988.

[11]Xu L, 2010. Bayesian Ying-Yang system, best harmony learning, and five action circling. Front Electr Electron Eng China, 5(3):281-328.

[12]Xu L, 2019a. Deep IA-BI and five actions in circling. Int Conf on Intelligent Science and Big Data Engineering, p.1-21.

[13]Xu L, 2019b. An overview and perspectives on bidirectional intelligence: Lmser duality, double IA harmony, and causal computation. IEEE/CAA J Autom Sin, 6(4):865-893.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE