Top

Neural Processing Letters

Published in:

10-01-2022

Continuous Recurrent Neural Networks Based on Function Satlins

Coexistence of Multiple Continuous Attractors

Authors: Yue Huang, Jiali Yu, Jinsong Leng, Bisen Liu, Zhang Yi

Published in: Neural Processing Letters | Issue 2/2022

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

The brief investigates the coexistence of multiple continuous attractors in a recurrent neural network, i.e., the symmetric saturated Satlins linear neural networks, based on a parameterized 2-D model. The saturated parts of the unliner activation function are the breakthrough for us to study the coexistence. The novel point of our research method is linearization in nonlinear networks. A continuous attractor is a set of connected stable equilibrium points. On the basis of the theorem that we proved on stability and existing findings on equilibria in mathematics, we propose the conditions for the coexistence of two or even multiple continuous attractors in a recurrent neural network. Simulations are also demonstrated to illustrate the theoretical results.

previous article A One-Layer Recurrent Neural Network for Interval-Valued Optimization Problem with Linear Constraints

next article DMH-FSL: Dual-Modal Hypergraph for Few-Shot Learning

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Yi Z, Tan K (2004) Convergence analysis of recurrent neural networks. Springer, US, pp 1–250CrossRef

Guo Z, Gong S, Wen S, Huang T (2019) Event-based synchronization control for memristive neural networks with time-varying delay. IEEE Trans. Cybern. 49(9):3268–3277CrossRef

Yu J, Yi Z (2016) Stability analysis and fuzzy control for uncertain delayed t-s nonlinear systems. Int. J. Fuzzy Syst. 18(6):1–8MathSciNetCrossRef

Chen W, Yu J, Yi Z, Hong Q (2021) The effect of coefficients on the continuous attractors in coupled highway neural networks. Neurocomputing 419:1–8CrossRef

Xiang W, Yu J, Yi Z, Wang C, Gao Q, Liao Y (2021) Coexistence of continuous attractors with different dimensions for neural networks - sciencedirect. Neurocomputing 429:25–32CrossRef

Chen T, Rubanova Y, Bettencourt J, DD (2018) Neural ordinary differential equations. In: 32nd conference on neural information processing systems

Haber E, Ruthotto L (2017) Stable architectures for deep neural networks. Inverse Prob 34(1):014004

Gou J, Wang L, Yi Z, Yuan Y, Ou W, Mao Q (2020) Weighted discriminative collaborative competitive representation for robust image classification. Neural Network 125(6):104–120CrossRef

Wang D, Ha M, Qiao J (2020) Data-driven iterative adaptive critic control towards an urban wastewater treatment plant. IEEE Trans Ind Electron 68(8):7362–7369CrossRef

10.

Yi Z, Luo G (2018) Multistability of a three-degree-of-freedom vibro-impact system. Commun Nonlinear Ence Numer Simul 57:331–341MathSciNetCrossRef

11.

Zhang X, Yang J, Tang L (2020) Three-way class-specific attribute reducts from the information viewpoint. Inf Sci 507:840–872MathSciNetCrossRef

12.

Xie X, Wen S, Zeng Z, Huang T (2018) Memristor-based circuit implementation of pulse-coupled neural network with dynamical threshold generator. Neurocomputing 284:10–16CrossRef

13.

Kriegeskorte N (2015) Deep neural networks: a new framework for modeling biological vision and brain information processing. Ann Rev Vis ence 1(1):417–446CrossRef

14.

Wang D, Ha M, Qiao J (2019) Self-learning optimal regulation for discrete-time nonlinear systems under event-driven formulation. IEEE Trans Autom Control 65:1272–1279MathSciNetCrossRef

15.

Eliasmith Ca (2007) Attractor network. Scholarpedia 2(10):1380CrossRef

16.

Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proceed National Acad Sci 81(10):3088–3092CrossRef

17.

Wu S, Amari S (2005) Computing with continuous attractors: stability and online aspects. Neural Comput 17:2215–2239MathSciNetCrossRef

18.

Wu S, Hamaguchi K, Amari S (2008) Dynamics and computation of continuous attractors. Neural Comput 20:994–1025MathSciNetCrossRef

19.

Seung HS (1998) Continuous attractors and oculomotor control. Neural Networks 11:1253–1258CrossRef

20.

Seung HS, Lee DD (2000) The manifold ways of perception. Science 290:2268–2269CrossRef

21.

Samsonovich A, Mcnaughton BL (1997) Path integration and cognitive mapping in a continuous attractor neural network model. J Neurosci 17(15):5900–5920CrossRef

22.

Wang C, Wu Y, Yu J (2016) Barrier lyapunov functions-based dynamic surface control for pure-feedback systems with full state constraints. IET Control Theory Appl 11:524–530MathSciNetCrossRef

23.

Lau J, Liang W, Tan K (2020) Motion control for piezoelectric-actuator-based surgical device using neural network and extended state observer. IEEE Trans Ind Electron 67:402–412CrossRef

24.

Zelati MC, Tone F (2012) Multivalued attractors and their approximation: Applications to the navier-stokes equations. Numerische Mathematik 122:421–441MathSciNetCrossRef

25.

Zhong C, Yang M, Sun C (2006) The existence of global attractors for the norm-to-weak continuous semigroup and application to the nonlinear reaction-diffusion equations. J Diff Equ 223:367–399MathSciNetCrossRef

26.

Yu J, Yi Z, Zhang L (2009) Representations of continuous attractors of recurrent neural networks. IEEE Trans Neural Network 20:368–372CrossRef

27.

Zou L, Tang H, Tan K, Zhang W (2009) Analysis of continuous attractors for 2-d linear threshold neural networks. IEEE Trans Neural Network 20:175–180CrossRef

28.

Yi Z, Tan KK, Lee TH (2003) Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Comput 15(3):639–662CrossRef

29.

Yi Z, Tan K (2004) Multistability analysis of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions, IEEE Trans. Neural Networks 15:329–336CrossRef

30.

Hahnloser RLT (1998) On the piecewise analysis of networks of linear threshold neurons. Neural Networks 11:691–697CrossRef

31.

Yi Z, Tan K, Lee TH (2003) Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Comput 15:639–662CrossRef

32.

Yu J, Mao H, Yi Z (2017) Parameter as a switch between dynamical states of a network in population decoding. Neural Network Learn Syst IEEE Trans 28(4):911–916CrossRef

33.

He M, Leng L, Yu J, Xu Y (2020) On the sum of k-frames in hilbert spaces. Mediterranean J Math 17(2):341–366MathSciNetCrossRef

34.

Tan K, Tang H, Zhang W (2005) Qualitative analysis for recurrent neural networks with linear threshold transfer functions. Circuit Syst 52:1003–1012MathSciNetMATH

35.

Zou L, Tang H, Tan K, Zhang W (2009) Analysis of continuous attractors for 2-d linear threshold neural networks. IEEE Trans. Neural Networks 20(1):175–80CrossRef

Title: Continuous Recurrent Neural Networks Based on Function Satlins
Coexistence of Multiple Continuous Attractors
Authors: Yue Huang
Jiali Yu
Jinsong Leng
Bisen Liu
Zhang Yi
Publication date: 10-01-2022
Publisher: Springer US
Published in: Neural Processing Letters / Issue 2/2022
Print ISSN: 1370-4621
Electronic ISSN: 1573-773X
DOI: https://doi.org/10.1007/s11063-021-10682-9

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Other articles of this Issue 2/2022

Fixed-Time Fuzzy Adaptive Tracking Control for Output-Constrained Uncertain Nonlinear Systems in Nonstrict-Feedback Form

A Dynamically Stabilized Recurrent Neural Network

MixNet: A Robust Mixture of Convolutional Neural Networks as Feature Extractors to Detect Stego Images Created by Content-Adaptive Steganography

Classification Algorithm Using Branches Importance

Emotional Neural Network Based on Improved CLPSO Algorithm For Time Series Prediction

Diffusion Modelling