Optimal Spherical Separability: Artificial Neural Networks

被引：0
|
作者：
Garimella, Rama Murthy [1 ]
Yaparla, Ganesh [1 ]
Singh, Rhishi Pratap [1 ]
机构：
[1] Int Inst Informat Technol, Hyderabad, India
来源：
ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2017, PT I | 2017年 / 10305卷
关键词：
25;
D O I：
10.1007/978-3-319-59153-7_29
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this research paper, the concept of hyper-spherical/hyper-ellipsoidal separability is introduced. Method of arriving at the optimal hypersphere (maximizing margin) separating two classes is discussed. By projecting the quantized patterns into higher dimensional space (as in encoders of error correcting code), the patterns are made hyper-spherically separable. Single/multiple layers of spherical/ellipsoidal neurons are proposed for multi-class classification. An associative memory based on hyper-ellipsoidal neuron is proposed.
引用
收藏
页码：327 / 338
页数：12
相关论文
共 50 条
  • [41] Stock market prediction using artificial neural networks with optimal feature transformation
    Kim, KJ
    Lee, WB
    [J]. NEURAL COMPUTING & APPLICATIONS, 2004, 13 (03): : 255 - 260
  • [42] An Optimal Adaptive under Frequency Load Shedding Using Artificial Neural Networks
    Wei Jinhua
    Bao Yanyan
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, BIG DATA AND ALGORITHMS (EEBDA), 2022, : 249 - 253
  • [43] Prediction of optimal warfarin maintenance dose using advanced artificial neural networks
    Grossi, Enzo
    Podda, Gian Marco
    Pugliano, Mariateresa
    Gabba, Silvia
    Verri, Annalisa
    Carpani, Giovanni
    Buscema, Massimo
    Casazza, Giovanni
    Cattaneo, Marco
    [J]. PHARMACOGENOMICS, 2014, 15 (01) : 29 - 37
  • [44] Selecting an Optimal Structure of Artificial Neural Networks for Characterizing RF Semiconductor Devices
    Dobes, Josef
    Pospisil, Ladislav
    Panko, Vaclav
    [J]. 53RD IEEE INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, 2010, : 1206 - 1209
  • [45] An improved method for automatically searching near-optimal artificial neural networks
    Almeida, Leandro A.
    Ludermir, Teresa
    [J]. 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 2235 - 2242
  • [46] Parallel Implementation of Genetic Algorithm for Searching Optimal Parameters of Artificial Neural Networks
    Nugroho, Eko Dwi
    Wibowo, Moh Edi
    Pulungan, Reza
    [J]. 2017 3RD INTERNATIONAL CONFERENCE ON SCIENCE AND TECHNOLOGY - COMPUTER (ICST), 2017, : 136 - 141
  • [47] Modelling optimal risk allocation in PPP projects using artificial neural networks
    Jin, Xiao-Hua
    Zhang, Guomin
    [J]. INTERNATIONAL JOURNAL OF PROJECT MANAGEMENT, 2011, 29 (05) : 591 - 603
  • [48] Stock market prediction using artificial neural networks with optimal feature transformation
    Kyoung-jae Kim
    Won Boo Lee
    [J]. Neural Computing & Applications, 2004, 13 : 255 - 260
  • [49] Optimal design of artificial neural networks by a multiobjective strategy: groundwater level predictions
    Giustolisi, Orazio
    Simeone, Vincenzo
    [J]. HYDROLOGICAL SCIENCES JOURNAL, 2006, 51 (03) : 502 - 523
  • [50] Face Recognition by Global Optimal Discriminant Features and Ensemble Artificial Neural Networks
    Wang, Jingjing
    Yin, Jianqin
    [J]. 2009 INTERNATIONAL SYMPOSIUM ON COMPUTER NETWORK AND MULTIMEDIA TECHNOLOGY (CNMT 2009), VOLUMES 1 AND 2, 2009, : 261 - +
12345