Incremental learning in autonomous systems: Evolving cnnectionist systems for on-line image and speech recognition

被引：0
|
作者：
Kasabov, N [1 ]
Zhang, D [1 ]
Pang, PS [1 ]
机构：
[1] Auckland Univ Technol, Knowledge Engn & Discovery Res Inst, Auckland, New Zealand
来源：
2005 IEEE WORKSHOP ON ADVANCED ROBOTICS AND ITS SOCIAL IMPACTS | 2005年
关键词：
autonomous systems; incremental learning; adaptive systems; multimodal systems; image recognition; speech recognition; evolving connectionist systems (ECOS); evolving growing cluster classifier (EGCC); online adaptation;
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
The paper presents an integrated approach to incremental learning in autonomous systems, that includes both pattern recognition and feature selection. The approach utilizes evolving connectionist systems (ECoS) and is applied on on-line image and speech pattern learning and recognition tasks.. The experiments show that ECoS are a suitable paradigm for building autonomous systems for learning and navigation in a new environment using both image and speech modalities.
引用
收藏
页码：120 / 125
页数：6
相关论文
共 50 条
  • [1] Incremental Similarity for real-time on-line incremental learning systems
    Reznakova, Marta
    Tencer, Lukas
    Cheriet, Mohamed
    PATTERN RECOGNITION LETTERS, 2016, 74 : 61 - 67
  • [2] Incremental learning algorithm for speech recognition
    Darjazini, Hisham
    Cheng, Qi
    Liyana-Pathirana, Ranjith
    INNOVATIONS AND ADVANCED TECHNIQUES IN COMPUTER AND INFORMATION SCIENCES AND ENGINEERING, 2007, : 231 - 235
  • [3] Incremental learning of feature space and classifier for on-line pattern recognition
    Ozawa, Seiichi
    Pang, Shaoning
    Kasabov, Nikola
    INTERNATIONAL JOURNAL OF KNOWLEDGE-BASED AND INTELLIGENT ENGINEERING SYSTEMS, 2006, 10 (01) : 57 - 65
  • [4] On-line feature selection for adaptive evolving connectionist systems
    Ozawa, Seiichi
    Pang, Shaoning
    Kasabov, Nikola
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2006, 2 (01): : 181 - 192
  • [5] ECOS - evolving connectionist systems - a new/old paradigm for on-line learning and knowledge engineering
    Kasabov, N
    FUTURE DIRECTIONS FOR INTELLIGENT SYSTEMS AND INFORMATION SCIENCES, 2000, 45 : 3 - 12
  • [6] Incremental Learning Through Graceful Degradations in Autonomous Systems
    Mani, Ganapathy
    Bhargava, Bharat
    Shivakumar, Basavesh
    Kobes, Jason
    2018 IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING (ICCC), 2018, : 25 - 32
  • [7] Sharing Computation Resources in Image and Speech Recognition for Embedded Systems
    Lee, Seung Eun
    ADVANCES IN COMPUTER SCIENCE, ENVIRONMENT, ECOINFORMATICS, AND EDUCATION, PT II, 2011, 215 : 150 - 156
  • [8] Evolving connectionist systems for on-line pattern classification of multimedia data
    Kasabov, Nikola
    Koprinska, Irena
    Iliev, Georgi
    PROCEEDINGS OF THE 9TH WSEAS INTERNATIONAL CONFERENCE ON NEURAL NETWORKS (NN' 08): ADVANCED TOPICS ON NEURAL NETWORKS, 2008, : 73 - +
  • [9] Multimodal systems for speech recognition
    Mamyrbayev, Orken Zh
    Alimhan, Keylan
    Amirgaliyev, Beibut
    Zhumazhanov, Bagashar
    Mussayeva, Dinara
    Gusmanova, Farida
    INTERNATIONAL JOURNAL OF MOBILE COMMUNICATIONS, 2020, 18 (03) : 314 - 326
  • [10] Incremental Learning for Fine-Grained Image Recognition
    Cao, Liangliang
    Hsiao, Jenhao
    de Juan, Paloma
    Li, Yuncheng
    Thomee, Bart
    ICMR'16: PROCEEDINGS OF THE 2016 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, 2016, : 363 - 366
12345