1
|
Wang Z, Li H, Ma L. Modern synergetic neural network for imbalanced small data classification. Sci Rep 2023; 13:15669. [PMID: 37735230 PMCID: PMC10514188 DOI: 10.1038/s41598-023-42689-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2023] [Accepted: 09/13/2023] [Indexed: 09/23/2023] Open
Abstract
Deep learning's performance on the imbalanced small data is substantially degraded by overfitting. Recurrent neural networks retain better performance in such tasks by constructing dynamical systems for robustness. Synergetic neural network (SNN), a synergetic-based recurrent neural network, has superiorities in eliminating recall errors and pseudo memories, but is subject to frequent association errors. Since the cause remains unclear, most subsequent studies use genetic algorithms to adjust parameters for better accuracy, which occupies the parameter optimization space and hinders task-oriented tuning. To solve the problem and promote SNN's application capability, we propose the modern synergetic neural network (MSNN) model. MSNN solves the association error by correcting the state initialization method in the working process, liberating the parameter optimization space. In addition, MSNN optimizes the attention parameter of the network with the error backpropagation algorithm and the gradient bypass technique to allow the network to be trained jointly with other network layers. The self-learning of the attention parameter empowers the adaptation to the imbalanced sample size, further improving the classification performance. In 75 classification tasks of small UC Irvine Machine Learning Datasets, the average rank of the MSNN achieves the best result compared to 187 neural and non-neural network machine learning methods.
Collapse
Affiliation(s)
- Zihao Wang
- Faculty of Computing, Harbin Institute of Technology, No.92, Xidazhi Street, Nangang District, Harbin, 150001, Heilongjiang, China
| | - Haifeng Li
- Faculty of Computing, Harbin Institute of Technology, No.92, Xidazhi Street, Nangang District, Harbin, 150001, Heilongjiang, China.
| | - Lin Ma
- Faculty of Computing, Harbin Institute of Technology, No.92, Xidazhi Street, Nangang District, Harbin, 150001, Heilongjiang, China
| |
Collapse
|
2
|
Wang Z, Li H, Ma L. Modern Synergetic Neural Network for Synthetic Aperture Radar Target Recognition. SENSORS (BASEL, SWITZERLAND) 2023; 23:2820. [PMID: 36905024 PMCID: PMC10006923 DOI: 10.3390/s23052820] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/12/2022] [Revised: 03/02/2023] [Accepted: 03/03/2023] [Indexed: 06/18/2023]
Abstract
Feature extraction is an important process for the automatic recognition of synthetic aperture radar targets, but the rising complexity of the recognition network means that the features are abstractly implied in the network parameters and the performances are difficult to attribute. We propose the modern synergetic neural network (MSNN), which transforms the feature extraction process into the prototype self-learning process by the deep fusion of an autoencoder (AE) and a synergetic neural network. We prove that nonlinear AEs (e.g., stacked and convolutional AE) with ReLU activation functions reach the global minimum when their weights can be divided into tuples of M-P inverses. Therefore, MSNN can use the AE training process as a novel and effective nonlinear prototypes self-learning module. In addition, MSNN improves learning efficiency and performance stability by making the codes spontaneously converge to one-hots with the dynamics of Synergetics instead of loss function manipulation. Experiments on the MSTAR dataset show that MSNN achieves state-of-the-art recognition accuracy. The feature visualization results show that the excellent performance of MSNN stems from the prototype learning to capture features that are not covered in the dataset. These representative prototypes ensure the accurate recognition of new samples.
Collapse
Affiliation(s)
| | - Haifeng Li
- Faculty of Computing, Harbin Institute of Technology, No. 92, Xidazhi Street, Nangang District, Harbin 150001, China
| | | |
Collapse
|
3
|
Zhang F, Zeng Z. Multistability and Stabilization of Fractional-Order Competitive Neural Networks With Unbounded Time-Varying Delays. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022; 33:4515-4526. [PMID: 33630741 DOI: 10.1109/tnnls.2021.3057861] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
This article investigates the multistability and stabilization of fractional-order competitive neural networks (FOCNNs) with unbounded time-varying delays. By utilizing the monotone operator, several sufficient conditions of the coexistence of equilibrium points (EPs) are obtained for FOCNNs with concave-convex activation functions. And then, the multiple μ -stability of delayed FOCNNs is derived by the analytical method. Meanwhile, several comparisons with existing work are shown, which implies that the derived results cover the inverse-power stability and Mittag-Leffler stability as special cases. Moreover, the criteria on the stabilization of FOCNNs with uncertainty are established by designing a controller. Compared with the results of fractional-order neural networks, the obtained results in this article enrich and improve the previous results. Finally, three numerical examples are provided to show the effectiveness of the presented results.
Collapse
|
4
|
Global exponential stability of discrete-time almost automorphic Caputo–Fabrizio BAM fuzzy neural networks via exponential Euler technique. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.108675] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
5
|
Viera-Martin E, Gómez-Aguilar JF, Solís-Pérez JE, Hernández-Pérez JA, Escobar-Jiménez RF. Artificial neural networks: a practical review of applications involving fractional calculus. THE EUROPEAN PHYSICAL JOURNAL. SPECIAL TOPICS 2022; 231:2059-2095. [PMID: 35194484 PMCID: PMC8853315 DOI: 10.1140/epjs/s11734-022-00455-3] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/07/2021] [Accepted: 01/13/2022] [Indexed: 05/13/2023]
Abstract
In this work, a bibliographic analysis on artificial neural networks (ANNs) using fractional calculus (FC) theory has been developed to summarize the main features and applications of the ANNs. ANN is a mathematical modeling tool used in several sciences and engineering fields. FC has been mainly applied on ANNs with three different objectives, such as systems stabilization, systems synchronization, and parameters training, using optimization algorithms. FC and some control strategies have been satisfactorily employed to attain the synchronization and stabilization of ANNs. To show this fact, in this manuscript are summarized, the architecture of the systems, the control strategies, and the fractional derivatives used in each research work, also, the achieved goals are presented. Regarding the parameters training using optimization algorithms issue, in this manuscript, the systems types, the fractional derivatives involved, and the optimization algorithm employed to train the ANN parameters are also presented. In most of the works found in the literature where ANNs and FC are involved, the authors focused on controlling the systems using synchronization and stabilization. Furthermore, recent applications of ANNs with FC in several fields such as medicine, cryptographic, image processing, robotic are reviewed in detail in this manuscript. Works with applications, such as chaos analysis, functions approximation, heat transfer process, periodicity, and dissipativity, also were included. Almost to the end of the paper, several future research topics arising on ANNs involved with FC are recommended to the researchers community. From the bibliographic review, we concluded that the Caputo derivative is the most utilized derivative for solving problems with ANNs because its initial values take the same form as the differential equations of integer-order.
Collapse
Affiliation(s)
- E. Viera-Martin
- Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Col. Palmira, C.P. 62490 Cuernavaca, Morelos Mexico
| | - J. F. Gómez-Aguilar
- CONACyT-Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Col. Palmira, C.P. 62490 Cuernavaca, Morelos Mexico
| | - J. E. Solís-Pérez
- Escuela Nacional de Estudios Superiores Unidad Juriquilla, Universidad Nacional Autónoma de México, Boulevard Juriquilla 3001, Juriquilla La Mesa, C.P. 76230 Juriquilla, Querétaro Mexico
| | - J. A. Hernández-Pérez
- Universidad Autónoma del Estado de Morelos/Centro de Investigación en Ingeniería y Ciencias Aplicadas, Av. Universidad No. 1001, Col Chamilpa, C.P. 62209 Cuernavaca, Morelos Mexico
| | - R. F. Escobar-Jiménez
- Tecnológico Nacional de México/CENIDET, Interior Internado Palmira S/N, Col. Palmira, C.P. 62490 Cuernavaca, Morelos Mexico
| |
Collapse
|
6
|
Shi J, Zeng Z. Design of In-Situ Learning Bidirectional Associative Memory Neural Network Circuit With Memristor Synapse. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2021. [DOI: 10.1109/tetci.2020.3005703] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
7
|
Novel methods to global Mittag-Leffler stability of delayed fractional-order quaternion-valued neural networks. Neural Netw 2021; 142:500-508. [PMID: 34280693 DOI: 10.1016/j.neunet.2021.07.005] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2021] [Revised: 05/21/2021] [Accepted: 07/05/2021] [Indexed: 11/23/2022]
Abstract
In this paper, a type of fractional-order quaternion-valued neural networks (FOQVNNs) with leakage and time-varying delays is established to simulate real-world situations, and the global Mittag-Leffler stability of the system is investigated by using the non-decomposition method. First, to avoid decomposing the system into two complex-valued systems or four real-valued systems, a new sign function for quaternion numbers is introduced based on the ones for real and complex numbers. And two novel lemmas for quaternion-valued sign function and Caputo fractional derivative are established in quaternion domain, which are used to investigate the stability of FOQVNNs. Second, a concise and flexible quaternion-valued state feedback controller is directly designed and a novel 1-norm Lyapunov function composed of the absolute values of real and imaginary parts is established. Then, based on the designed quaternion-valued state feedback controller and the proposed lemmas, some sufficient conditions are given to ensure the global Mittag-Leffler stability of the system. Finally, a numerical simulation is given to verify the theoretical results.
Collapse
|
8
|
Controller design for finite-time and fixed-time stabilization of fractional-order memristive complex-valued BAM neural networks with uncertain parameters and time-varying delays. Neural Netw 2020; 130:60-74. [DOI: 10.1016/j.neunet.2020.06.021] [Citation(s) in RCA: 48] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Revised: 06/04/2020] [Accepted: 06/28/2020] [Indexed: 11/19/2022]
|
9
|
Xu Y, Li Y, Li W, Feng J. Synchronization of multi-links impulsive fractional-order complex networks via feedback control based on discrete-time state observations. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.04.024] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
10
|
Zhang L, Yang Y. Finite time impulsive synchronization of fractional order memristive BAM neural networks. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2019.12.056] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
11
|
Qiao Y, Yan H, Duan L, Miao J. Finite-time synchronization of fractional-order gene regulatory networks with time delay. Neural Netw 2020; 126:1-10. [PMID: 32172040 DOI: 10.1016/j.neunet.2020.02.004] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2019] [Revised: 12/16/2019] [Accepted: 02/10/2020] [Indexed: 10/25/2022]
Abstract
As multi-gene networks transmit signals and products by synchronous cooperation, investigating the synchronization of gene regulatory networks may help us to explore the biological rhythm and internal mechanisms at molecular and cellular levels. We aim to induce a type of fractional-order gene regulatory networks to synchronize at finite-time point by designing feedback controls. Firstly, a unique equilibrium point of the network is proved by applying the principle of contraction mapping. Secondly, some sufficient conditions for finite-time synchronization of fractional-order gene regulatory networks with time delay are explored based on two kinds of different control techniques and fractional Lyapunov function approach, and the corresponding setting time is estimated. Finally, some numerical examples are given to demonstrate the effectiveness of the theoretical results.
Collapse
Affiliation(s)
- Yuanhua Qiao
- College of Applied Sciences, Beijing University of Technology, Beijing 100124, China
| | - Hongyun Yan
- College of Applied Sciences, Beijing University of Technology, Beijing 100124, China
| | - Lijuan Duan
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China; Beijing Key Laboratory of Trusted Computing, Beijing 100124, China; National Engineering Laboratory for Key Technologies of Information Security Level Protection, Beijing 100124, China.
| | - Jun Miao
- School of Computer Science, Beijing Information Science and Technology University, Beijing 100101, China
| |
Collapse
|
12
|
Global Mittag-Leffler stability and synchronization of discrete-time fractional-order complex-valued neural networks with time delay. Neural Netw 2020; 122:382-394. [DOI: 10.1016/j.neunet.2019.11.004] [Citation(s) in RCA: 44] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2019] [Revised: 10/06/2019] [Accepted: 11/04/2019] [Indexed: 11/21/2022]
|
13
|
Hybrid Control Scheme for Projective Lag Synchronization of Riemann–Liouville Sense Fractional Order Memristive BAM NeuralNetworks with Mixed Delays. MATHEMATICS 2019. [DOI: 10.3390/math7080759] [Citation(s) in RCA: 35] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
This sequel is concerned with the analysis of projective lag synchronization of Riemann–Liouville sense fractional order memristive BAM neural networks (FOMBNNs) with mixed time delays via hybrid controller. Firstly, a new type of hybrid control scheme, which is the combination of open loop control and adaptive state feedback control is designed to guarantee the global projective lag synchronization of the addressed FOMBNNs model. Secondly, by using a Lyapunov–Krasovskii functional and Barbalet’s lemma, a new brand of sufficient criterion is proposed to ensure the projective lag synchronization of the FOMBNNs model considered. Moreover, as special cases by using a hybrid control scheme, some sufficient conditions are derived to ensure the global projective synchronization, global complete synchronization and global anti-synchronization for the FOMBNNs model considered. Finally, numerical simulations are provided to check the accuracy and validity of our obtained synchronization results.
Collapse
|
14
|
Fan Y, Huang X, Wang Z, Li Y. Improved quasi-synchronization criteria for delayed fractional-order memristor-based neural networks via linear feedback control. Neurocomputing 2018. [DOI: 10.1016/j.neucom.2018.03.060] [Citation(s) in RCA: 32] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
15
|
Global Mittag-Leffler Synchronization for Fractional-Order BAM Neural Networks with Impulses and Multiple Variable Delays via Delayed-Feedback Control Strategy. Neural Process Lett 2018. [DOI: 10.1007/s11063-018-9801-0] [Citation(s) in RCA: 35] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
16
|
Tao B, Xiao M, Sun Q, Cao J. Hopf bifurcation analysis of a delayed fractional-order genetic regulatory network model. Neurocomputing 2018. [DOI: 10.1016/j.neucom.2017.09.018] [Citation(s) in RCA: 60] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
17
|
Yang X, Li C, Huang T, Song Q, Huang J. Global Mittag-Leffler Synchronization of Fractional-Order Neural Networks Via Impulsive Control. Neural Process Lett 2017. [DOI: 10.1007/s11063-017-9744-x] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
18
|
Ding X, Cao J, Zhao X, Alsaadi FE. Mittag-Leffler synchronization of delayed fractional-order bidirectional associative memory neural networks with discontinuous activations: state feedback control and impulsive control schemes. Proc Math Phys Eng Sci 2017; 473:20170322. [PMID: 28878565 DOI: 10.1098/rspa.2017.0322] [Citation(s) in RCA: 26] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2017] [Accepted: 06/30/2017] [Indexed: 11/12/2022] Open
Abstract
This paper is concerned with the drive-response synchronization for a class of fractional-order bidirectional associative memory neural networks with time delays, as well as in the presence of discontinuous activation functions. The global existence of solution under the framework of Filippov for such networks is firstly obtained based on the fixed-point theorem for condensing map. Then the state feedback and impulsive controllers are, respectively, designed to ensure the Mittag-Leffler synchronization of these neural networks and two new synchronization criteria are obtained, which are expressed in terms of a fractional comparison principle and Razumikhin techniques. Numerical simulations are presented to validate the proposed methodologies.
Collapse
Affiliation(s)
- Xiaoshuai Ding
- School of Mathematics, and Research Center for Complex Systems and Network Sciences, Southeast University, Nanjing 210096, People's Republic of China.,School of Education, Xizang Minzu University, Xianyang 712082, People's Republic of China
| | - Jinde Cao
- School of Mathematics, and Research Center for Complex Systems and Network Sciences, Southeast University, Nanjing 210096, People's Republic of China.,Department of Mathematics, Faculty of Science, Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Xuan Zhao
- School of Mathematics, and Research Center for Complex Systems and Network Sciences, Southeast University, Nanjing 210096, People's Republic of China
| | - Fuad E Alsaadi
- Electrical and Computer Engineering Department, Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| |
Collapse
|
19
|
Kinh CT, Hien LV, Ke TD. Power-Rate Synchronization of Fractional-Order Nonautonomous Neural Networks with Heterogeneous Proportional Delays. Neural Process Lett 2017. [DOI: 10.1007/s11063-017-9637-z] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
|
20
|
Mittag–Leffler Stability and Global Asymptotically
$$\omega $$
ω
-Periodicity of Fractional-Order BAM Neural Networks with Time-Varying Delays. Neural Process Lett 2017. [DOI: 10.1007/s11063-017-9634-2] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
21
|
Yang X, Li C, Huang T, Song Q, Chen X. Quasi-uniform synchronization of fractional-order memristor-based neural networks with delay. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2017.01.014] [Citation(s) in RCA: 43] [Impact Index Per Article: 6.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
22
|
|
23
|
Wu A, Liu L, Huang T, Zeng Z. Mittag-Leffler stability of fractional-order neural networks in the presence of generalized piecewise constant arguments. Neural Netw 2017; 85:118-127. [DOI: 10.1016/j.neunet.2016.10.002] [Citation(s) in RCA: 77] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2016] [Revised: 09/30/2016] [Accepted: 10/09/2016] [Indexed: 11/24/2022]
|
24
|
Xiao J, Zhong S, Li Y, Xu F. Finite-time Mittag-Leffler synchronization of fractional-order memristive BAM neural networks with time delays. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2016.09.049] [Citation(s) in RCA: 123] [Impact Index Per Article: 17.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
25
|
Global Mittag–Leffler stability for a coupled system of fractional-order differential equations on network with feedback controls. Neurocomputing 2016. [DOI: 10.1016/j.neucom.2016.05.080] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
26
|
Liu L, Wu A, Song X. Global [Formula: see text] stabilization of fractional-order memristive neural networks with time delays. SPRINGERPLUS 2016; 5:1034. [PMID: 27462482 PMCID: PMC4938841 DOI: 10.1186/s40064-016-2374-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/25/2016] [Accepted: 05/19/2016] [Indexed: 11/10/2022]
Abstract
This article is concerned with the global [Formula: see text] stabilization for a class of fractional-order memristive neural networks with time delays (FMDNNs). Two kinds of control scheme (i.e., state feedback control law and output feedback control law) are employed to stabilize a class of FMDNNs. Several stabilization conditions in form of algebraic criteria are presented based on a new fractional-order Lyapunov function method and Leibniz rule. Some examples are given to substantiate the effectiveness of the presented theoretical results.
Collapse
Affiliation(s)
- Ling Liu
- />College of Mathematics and Statistics, Hubei Normal University, Huangshi, 435002 China
| | - Ailong Wu
- />College of Mathematics and Statistics, Hubei Normal University, Huangshi, 435002 China
| | - Xingguo Song
- />School of Mechanical Engineering, Southwest Jiaotong University, Chengdu, 610031 China
| |
Collapse
|