Extending the Universal Approximation Theorem for a Broad Class of Hypercomplex-Valued Neural Networks

被引:3
|
作者
Vital, Wington L. [1 ]
Vieira, Guilherme [1 ]
Valle, Marcos Eduardo [1 ]
机构
[1] Univ Estadual Campinas, Campinas, Brazil
来源
INTELLIGENT SYSTEMS, PT II | 2022年 / 13654卷
基金
巴西圣保罗研究基金会;
关键词
Hypercomplex algebras; Neural networks; Universal approximation theorem;
D O I
10.1007/978-3-031-21689-3_45
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets. As an existential result, the universal approximation theorem supports the use of neural networks for various applications, including regression and classification tasks. The universal approximation theorem is not limited to real-valued neural networks but also holds for complex, quaternion, tessarines, and Clifford-valued neural networks. This paper extends the universal approximation theorem for a broad class of hypercomplex-valued neural networks. Precisely, we first introduce the concept of non-degenerate hypercomplex algebra. Complex numbers, quaternions, and tessarines are examples of non-degenerate hypercomplex algebras. Then, we state the universal approximation theorem for hypercomplex-valued neural networks defined on a non-degenerate algebra.
引用
收藏
页码:646 / 660
页数:15
相关论文
共 50 条
  • [41] Conditions for Radial Basis Function Neural networks to Universal Approximation and Numerical Experiments
    Nong, Jifu
    [J]. 2013 25TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2013, : 2193 - 2197
  • [42] Universal Approximation Power of Deep Residual Neural Networks Through the Lens of Control
    Tabuada, Paulo
    Gharesifard, Bahman
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (05) : 2715 - 2728
  • [43] A Universal Approximation Result for Difference of Log-Sum-Exp Neural Networks
    Calafiore, Giuseppe C.
    Gaubert, Stephane
    Possieri, Corrado
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (12) : 5603 - 5612
  • [44] Stochastic Exponential Robust Stability of a Class of Complex-Valued Neural Networks
    Xu, Xiao-Hui
    Shi, Ji-Zhong
    Yan, Chao
    Zhang, Ji-Ye
    Xu, Yan-Hai
    [J]. Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2019, 48 (03): : 374 - 380
  • [45] Approximation capabilities of multilayer fuzzy neural networks on the set of fuzzy-valued functions
    Huang, Huan
    Wu, Congxin
    [J]. INFORMATION SCIENCES, 2009, 179 (16) : 2762 - 2773
  • [46] Approximation of fuzzy-valued functions by regular fuzzy neural networks and the accuracy analysis
    Huang, Huan
    Wu, Congxin
    [J]. SOFT COMPUTING, 2014, 18 (12) : 2525 - 2540
  • [47] Approximation of fuzzy-valued functions by regular fuzzy neural networks and the accuracy analysis
    Huan Huang
    Congxin Wu
    [J]. Soft Computing, 2014, 18 : 2525 - 2540
  • [48] Uniqueness Theorem of Complex-Valued Neural Networks with Polar-Represented Activation Function
    Kobayashi, Masaki
    [J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2015, E98A (09): : 1937 - 1943
  • [49] Universal approximation of polygonal fuzzy neural networks in sense of K-integral norms
    GuiJun Wang
    XiaoPing Li
    [J]. Science China Information Sciences, 2011, 54 : 2307 - 2323
  • [50] The universal approximation capabilities of 2pi-periodic approximate identity neural networks
    Fard, Saeed Panahian
    Zainuddin, Zarita
    [J]. PROCEEDINGS OF 2013 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND CLOUD COMPUTING COMPANION (ISCC-C), 2014, : 793 - 798