Formal Concept Refinement by Deep Cognitive Machine Learning

被引：0
|
作者：
Zatarain, Omar A. [1 ]
Wang, Yingxu
机构：
[1] Univ Calgary, Int Inst Cognit Informat & Cognit Comp ICIC, Lab Computat Intelligence Cognit Syst Denotat Mat, Dept Elect & Comp Engn,Schulich Sch Engn, 2500 Univ Dr NW, Calgary, AB T2N 1N4, Canada
来源：
2017 IEEE 16TH INTERNATIONAL CONFERENCE ON COGNITIVE INFORMATICS & COGNITIVE COMPUTING (ICCI*CC) | 2017年
基金：
加拿大自然科学与工程研究理事会;
关键词：
Cognitive machine learning; concept refinement; algorithm; unsupervised learning; knowledge learning; computational linguistics; cognitive computation; DENOTATIONAL MATHEMATICS; INTELLIGENT; LANGUAGE; ALGEBRA;
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：
Concept generation and refinement is a process to generate and improve machine's knowledge base represented by a comprehensive set of formal concepts. An unsupervised algorithm for concept refinement is developed for autonomously upgrading and enhancing acquired concepts of knowledge in a cognitive knowledge base built by cognitive robots and systems. The concept refinement algorithm is implemented based on a set of rules of concept algebra and semantic analyses. Experimental results demonstrate that cognitive machines can autonomously refine their knowledge by improving acquired concepts in a dynamic process mimicking human learning mechanisms in deep machine learning and cognitive computing.
引用
收藏
页码：71 / 78
页数：8
相关论文
共 50 条
  • [21] Deep unsupervised learning on a desktop PC: a primer for cognitive scientists
    Testolin, Alberto
    Stoianov, Ivilin
    De Grazia, Michele De Filippo
    Zorzi, Marco
    FRONTIERS IN PSYCHOLOGY, 2013, 4
  • [22] Deep Weighted Extreme Learning Machine
    Wang, Tianlei
    Cao, Jiuwen
    Lai, Xiaoping
    Chen, Badong
    COGNITIVE COMPUTATION, 2018, 10 (06) : 890 - 907
  • [23] A Parameter Refinement Method for Ptychography Based on Deep Learning Concepts
    Guzzi, Francesco
    Kourousias, George
    Gianoncelli, Alessandra
    Bille, Fulvio
    Carrato, Sergio
    CONDENSED MATTER, 2021, 6 (04):
  • [24] Fraud Detection Using Machine Learning and Deep Learning
    Gandhar A.
    Gupta K.
    Pandey A.K.
    Raj D.
    SN Computer Science, 5 (5)
  • [25] Machine learning in construction: From shallow to deep learning
    Xu, Yayin
    Zhou, Ying
    Sekula, Przemyslaw
    Ding, Lieyun
    DEVELOPMENTS IN THE BUILT ENVIRONMENT, 2021, 6
  • [26] Meta-cognitive online sequential extreme learning machine for imbalanced and concept-drifting data classification
    Mirza, Bilal
    Lin, Zhiping
    NEURAL NETWORKS, 2016, 80 : 79 - 94
  • [27] A Machine Learning Approach to Cognitive Radar Detection
    Metcalf, Justin
    Blunt, Shannon D.
    Himed, Braham
    2015 IEEE INTERNATIONAL RADAR CONFERENCE (RADARCON), 2015, : 1405 - 1411
  • [28] Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review
    Khosravi, Bardia
    Rouzrokh, Pouria
    Faghani, Shahriar
    Moassefi, Mana
    Vahdati, Sanaz
    Mahmoudi, Elham
    Chalian, Hamid
    Erickson, Bradley J.
    DIAGNOSTICS, 2022, 12 (10)
  • [29] False Alert Detection Based on Deep Learning and Machine Learning
    Li, Shudong
    Qin, Danyi
    Wu, Xiaobo
    Li, Juan
    Li, Baohui
    Han, Weihong
    INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS, 2022, 18 (01)
  • [30] Wavelet extreme learning machine and deep learning for data classification
    Yahia, Siwar
    Said, Salwa
    Zaied, Mourad
    NEUROCOMPUTING, 2022, 470 : 280 - 289
12345