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：
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
  • [1] Optimal Configuration of Artificial Neural Networks
    Dua, Vivek
    [J]. 16TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING AND 9TH INTERNATIONAL SYMPOSIUM ON PROCESS SYSTEMS ENGINEERING, 2006, 21 : 1599 - 1604
  • [2] Domains of Competence of Artificial Neural Networks Using Measures of Separability of Classes
    Luengo, Julian
    Herrera, Francisco
    [J]. BIO-INSPIRED SYSTEMS: COMPUTATIONAL AND AMBIENT INTELLIGENCE, PT 1, 2009, 5517 : 81 - 88
  • [3] Testing selected optimal descriptors with artificial neural networks
    Pogliani, Lionello
    Vicente de Julian-Ortiz, Jesus
    [J]. RSC ADVANCES, 2013, 3 (34): : 14710 - 14721
  • [4] Accelerating Optimal Test Planning With Artificial Neural Networks
    Mell, Philipp
    Karle, Fabian
    Herzig, Thomas
    Dazer, Martin
    Bertsche, Bernd
    [J]. 2022 68TH ANNUAL RELIABILITY AND MAINTAINABILITY SYMPOSIUM (RAMS 2022), 2022,
  • [5] Optimal architecture for artificial neural networks as pressure estimator
    Modesto de Souza, Rui Gabriel
    Brentan, Bruno Melo
    Lima, Gustavo Meirelles
    [J]. RBRH-REVISTA BRASILEIRA DE RECURSOS HIDRICOS, 2021, 26
  • [6] Hybrid heuristics for optimal design of Artificial Neural Networks
    Abraham, A
    Nath, B
    [J]. DEVELOPMENTS IN SOFT COMPUTING, 2001, : 15 - 22
  • [7] THE USE OF ARTIFICIAL NEURAL NETWORKS FOR OPTIMAL MESSAGE ROUTING
    WANG, CJ
    WEISSLER, PN
    [J]. IEEE NETWORK, 1995, 9 (02): : 16 - 24
  • [8] Quantifying the separability of data classes in neural networks
    Schilling, Achim
    Maier, Andreas
    Gerum, Richard
    Metzner, Claus
    Krauss, Patrick
    [J]. NEURAL NETWORKS, 2021, 139 : 278 - 293
  • [9] Optimal operation of a separation plant using Artificial Neural Networks
    Altissimi, R
    Brambilla, A
    Deidda, A
    Semino, D
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 1998, 22 : S939 - S942
  • [10] Optimal learning in artificial neural networks: A review of theoretical results
    Bianchini, M
    Gori, M
    [J]. NEUROCOMPUTING, 1996, 13 (2-4) : 313 - 346
12345