Learning by switching generation and reasoning methods in several knowledge representations - towards the simulation of human learning process

被引：0

作者：

Umano, M ^{[1
]}

Matsumoto, Y ^{[1
]}

Uno, Y ^{[1
]}

Seta, K ^{[1
]}

机构：

[1] Univ Osaka Prefecture, Coll Integrated Arts & Sci, Dept Math & Informat Sci, Sakai, Osaka 5998531, Japan

来源：

PROCEEDINGS OF THE 2002 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOL 1 & 2 | 2002年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

When we solve a problem, we firstly have no knowledge and gradually acquire some piece of knowledge by observing new data, and at last arrive at complete knowledge for solving the problem. We have a simple form of specific knowledge in the first stage and a complex form of general one in the final stage. To simulate this kind of learning mechanism, we must combine several kinds of learning methods in several stages. In this paper, we proposed a method of not only reconstructing rules and switching reasoning methods in each knowledge representation but also switching rule generation methods in several knowledge representation. We simulated the method by applying to the iris classification problem by R.A. Fisher.

引用

页码：809 / 814

页数：6

共 50 条

[1] Learning by Switching Generation and Reasoning Methods-Acquisition of Meta-knowledge for Switching with Reinforcement Learning
Tomaru, Masahiro
Umano, Motohide
Matsumoto, Yuji
Seta, Kazuhisa
[J]. 2008 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-5, 2008, : 1930 - +
[2] Learning distributed representations of knowledge that preserve deductive reasoning
Chen, Ya
Mensah, Samuel
Li, Junpeng
[J]. KNOWLEDGE-BASED SYSTEMS, 2024, 293
[3] Learning by switching knowledge representations - Limiting the number of stored data
Matsumoto, Yuji
Umano, Motohide
Tomaru, Masahiro
Seta, Kazuhisa
[J]. 2006 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-5, 2006, : 144 - +
[4] Reasoning Like Human: Hierarchical Reinforcement Learning for Knowledge Graph Reasoning
Wan, Guojia
Pan, Shirui
Gong, Chen
Zhou, Chuan
Haffari, Gholamreza
[J]. PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 1926 - 1932
[5] Towards combining commonsense reasoning and knowledge acquisition to guide deep learning
Mohan Sridharan
Tiago Mota
[J]. Autonomous Agents and Multi-Agent Systems, 2023, 37
[6] Towards combining commonsense reasoning and knowledge acquisition to guide deep learning
Sridharan, Mohan
Mota, Tiago
[J]. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2023, 37 (01)
[7] A New Methodology of Knowledge Point Sequence Generation and Learning Path Recommendation by Knowledge Reasoning
Zhou, Jia
Liang, Dongling
[J]. International Journal of Emerging Technologies in Learning, 2023, 18 (13) : 178 - 192
[8] Towards Human Activity Reasoning with Computational Logic and Deep Learning
Prapas, Ioannis
Paliouras, Georgios
Artikis, Alexander
Baskiotis, Nicolas
[J]. 10TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE (SETN 2018), 2018,
[9] Generation of agent simulation models by using process mining methods on the example of E-learning process
Dorrer, Mikhail
Dorrer, Alexandra
[J]. INTERNATIONAL SCIENTIFIC CONFERENCE ON APPLIED PHYSICS, INFORMATION TECHNOLOGIES AND ENGINEERING (APITECH-2019), 2019, 1399
[10] Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction
Chung, Chanyoung
Whang, Joyce Jiyoung
[J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 4208 - 4216

← 1 2 3 4 5 →