• Title/Summary/Keyword: recurrent

Search Result 3,512, Processing Time 0.036 seconds

Identification of Finite Automata Using Recurrent Neural Networks

  • Won, Sung-Hwan;Park, Cheol-Hoon
    • Proceedings of the IEEK Conference
    • /
    • 2008.06a
    • /
    • pp.667-668
    • /
    • 2008
  • This paper demonstrates that the recurrent neural networks can be used successfully for the identification of finite automata (FAs). A new type of recurrent neural network (RNN) is proposed and the offline training algorithm, regulated Levenberg-Marquadt (LM) algorithm, for the network is developed. Simulation result shows that the identification and the extraction of FAs are practically achievable.

  • PDF

CHAIN RECURRENCE AND ATTRACTORS IN GENERAL DYNAMICAL SYSTEMS

  • Lee, Kyung-Bok;Park, Jong-Shu
    • Communications of the Korean Mathematical Society
    • /
    • v.22 no.4
    • /
    • pp.575-586
    • /
    • 2007
  • We introduce here notions of chain recurrent sets, attractors and its basins for general dynamical systems and prove important properties including (i) the chain recurrent set CR(f) of f on a metric space (X, d) is the complement of the union of sets B(A) -A as A varies over the collection of attractors and (ii) genericity of general dynamical systems.

DISTRIBUTIONAL CHAOS AND DISTRIBUTIONAL CHAOS IN A SEQUENCE OCCURRING ON A SUBSET OF THE ONE-SIDED SYMBOLIC SYSTEM

  • Tang, Yanjie;Yin, Jiandong
    • Bulletin of the Korean Mathematical Society
    • /
    • v.57 no.1
    • /
    • pp.95-108
    • /
    • 2020
  • The aim of this paper is to show that for the one-sided symbolic system, there exist an uncountable distributively chaotic set contained in the set of irregularly recurrent points and an uncountable distributively chaotic set in a sequence contained in the set of proper positive upper Banach density recurrent points.

Sliding Mode Control based on Recurrent Neural Network (회귀신경망을 이용한 슬라이딩 모드 제어)

  • 홍경수;이건복
    • Proceedings of the Korean Society of Machine Tool Engineers Conference
    • /
    • 2000.10a
    • /
    • pp.135-139
    • /
    • 2000
  • This research proposes a nonlinear sliding mode control. The sliding mode control is designed according to Lyapunov function. The equivalent control term is estimated by neural network. To estimate the unknown part in the control law in on-line fashion, A recurrent neural network is given as on-line estimator. The stability of the control system is guaranteed owing to the on-line learning ability of the recurrent neural network. It is certificated through simulation results to be applied to nonlinear system that the function approximation and the proposed control scheme is very effective.

  • PDF

ON FINSLER SPACE OF RECURRENT CURVATURE TENSORS

  • Rastogi, S.C.
    • Kyungpook Mathematical Journal
    • /
    • v.20 no.1
    • /
    • pp.37-45
    • /
    • 1980
  • The Riemannian space of recurrent curvature was defined and studied by Ruse [8] and Walker [10]. In 1963, $M{\acute{o}}or$ [4] generalised this idea for Finsler spaces and defined and studied Finsler spaces of recurrent curvature. These spaces for various curvature tensors have subsequently been studied by Mishra and Pande [1], Sen [9] and Misra [3] etc. The purpose of the present paper is to study Finsler space based on the recurrency of the curvature tensors derived from non-linear connections.

  • PDF

Conformally Flat Totally Umbilical Submanifolds in Some Semi-Riemannian Manifolds

  • Ewert-Krzemieniewski, Stanislaw
    • Kyungpook Mathematical Journal
    • /
    • v.48 no.2
    • /
    • pp.183-194
    • /
    • 2008
  • We prove that totally umbilical submanifold M of an extended quasi-recurren manifold is also extended quasi-recurrent. If, moreover, M is conformally flat then, locally, M is isometric to the manifold with known metric. Some curvature properties of such submanifold are investigated. Making use of these results we shall prove the existence of totally umbilical submanifold being pseudosymmetric in the sense of Ryszard Deszcz and satisfying some other curvature conditions.

Network Packet Classification Using Convolution Neural Network and Recurrent Neural Network (Convolution Neural Network와 Recurrent Neural Network를 활용한 네트워크 패킷 분류)

  • Lim, Hyun-Kyo;Kim, Ju-Bong;Han, Youn-Hee
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2018.05a
    • /
    • pp.16-18
    • /
    • 2018
  • 최근 네트워크 상에 새롭고 다양한 어플리케이션들이 생겨나면서 이에 따른 적절한 어플리케이션별 서비스 제공을 위한 패킷 분류 방법이 요구되고 있다. 이로 인하여 딥 러닝 기술이 발전 하면서 이를 이용한 네트워크 트래픽 분류 방법들이 제안되고 있다. 따라서, 본 논문에서는 딥 러닝 기술 중 Convolution Neural Network 와 Recurrent Neural Network 를 동시에 활용한 네트워크 패킷 분류 방법을 제안한다.

RECURRENT STRUCTURE JACOBI OPERATOR OF REAL HYPERSURFACES IN COMPLEX HYPERBOLIC TWO-PLANE GRASSMANNIANS

  • JEONG, IMSOON;WOO, CHANGHWA
    • Journal of applied mathematics & informatics
    • /
    • v.39 no.3_4
    • /
    • pp.327-338
    • /
    • 2021
  • In this paper, we have introduced a new notion of recurrent structure Jacobi of real hypersurfaces in complex hyperbolic two-plane Grassmannians G*2(ℂm+2). Next, we show a non-existence property of real hypersurfaces in G*2(ℂm+2) satisfying such a curvature condition.