CN110956250A - Double-memristor Hopfield neural network model with coexisting multiple attractors - Google Patents
Double-memristor Hopfield neural network model with coexisting multiple attractors Download PDFInfo
- Publication number
- CN110956250A CN110956250A CN201811127495.9A CN201811127495A CN110956250A CN 110956250 A CN110956250 A CN 110956250A CN 201811127495 A CN201811127495 A CN 201811127495A CN 110956250 A CN110956250 A CN 110956250A
- Authority
- CN
- China
- Prior art keywords
- neural network
- memristor
- hopfield neural
- network model
- neuron
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Semiconductor Memories (AREA)
Abstract
The invention discloses a double-memristor Hopfield neural network model with coexisting multiple attractors, and relates to the field of application of Hopfield neural network models. The invention introduces two memristors in a three-neuron Hopfield neural network to respectively replace two resistive coupling quantities in an original coupling weight matrix. By changing the initial value of the state variable in the model, different types of multi-attractor coexistence phenomena can be shown under different internal parameters of the memristor, so that complex dynamic behaviors in the brain are simulated.
Description
Technical Field
The invention relates to the application field of Hopfield neural network models, in particular to a double-memristor Hopfield neural network model with coexisting multiple attractors.
Background
It is known that human beings have much better abilities of movement, cognition, learning, etc. than other mammals, and the formation of these abilities depends mainly on the cooperative cooperation among neurons in the complex neural network system in the human body. From the beginning of the last century, people construct various artificial neural network models which can meet different requirements of people on the basis of the research on the biological neural network, and continuously improve and perfect the artificial neural network models. Among the numerous neural network models, the Hopfield neural network proposed by professor john Hopfield is an important milestone in the development history of neural networks.
The Hopfield neural network model is a feedback type neural network, and has the most important characteristic that the Hopfield neural network model has an associative memory function and can copy the functions of the human brain. In recent years, more and more evidences show that complex chaotic dynamics exist in the brain, and the Hopfield neural network can better simulate chaotic behaviors in the brain and is an important model for artificial neural computation. The Hopfield neural network model embodies the coupling connection weight of synapses between neurons and has good reference function for deeply researching and simulating brain functions of people.
The concept of the memristor is firstly proposed by professor Chuai begonia, and the memristor is a nonlinear resistor with a memory function. Research shows that memristors are the best way for realizing artificial neural network synapses by hardware, which can be found by people so far. A Hopfield neural network model based on memristions is constructed by using the memristions, and the coexistence behavior of multiple attractors is found in the new model. The multi-stability research is beneficial to further understanding the practical application value of the Hopfield neural network in associative memory and pattern recognition.
Disclosure of Invention
In view of the above situation, the present invention provides a dual memristive Hopfield neural network model with coexisting multiple attractors.
In order to achieve the purpose, the invention adopts the following technical scheme:
a double-memristor Hopfield neural network model with coexisting multiple attractors is constructed by introducing two memristors into a three-neuron Hopfield neural network, respectively replacing two resistive coupling quantities in an original coupling weight matrix and simulating biological synapses by using the memristors; by changing the initial value of the state variable in the model, different types of multi-attractor coexistence phenomena are shown under different internal parameters of the memristor, so that complex dynamic behaviors in the brain are simulated.
Further, the double-memristive Hopfield neural network model comprises a three-neuron memristive Hopfield neural network model and two non-ideal hyperbolic memristive models.
Has the advantages that:
the method comprises the steps of replacing two coupling weights in a synapse weight matrix of a three-neuron Hopfield neural network with memristive coupling weights respectively, simulating biological synapses by using memristors, and constructing a double-memristive Hopfield neural network model capable of generating coexistence of multiple attractors, wherein the model is used for simulating complex and rich dynamic behaviors in the biological neural network and revealing a complex and singular phenomenon of multi-stability.
Drawings
FIG. 1 is a connection topology diagram of a dual memristive Hopfield neural network model with co-existing multiple attractors, in accordance with the present invention;
FIG. 2(a) is a memristor W of the present invention2Internal parameter b of 0.2, memristor W1With the internal parameter a of the state variable x1A bifurcation graph of the changes;
FIG. 2(b) is a memristor W of the present invention1Internal parameter a of 0.1, memristor W2With the internal parameter b of the state variable x1A bifurcation graph of the changes;
FIG. 3(a) is a memristor W of the present invention2Internal parameter b of 0.2, memristor W1When the internal parameter a is-0.1835, x1-x3Phase rail diagram on the plane;
FIG. 3(b) is a memristor W of the present invention2Internal parameter b of 0.2, memristor W1When the internal parameter a of (2) is 0.15, x1-x3Phase rail diagram on the plane;
FIG. 4(a) is a memristor W of the present invention1Internal parameter a of 0.1, memristor W2When the internal parameter b is-0.15, x1-x3Phase rail diagram on the plane;
FIG. 4(b) is a memristor W of the present invention1Internal parameter a of 0.1, memristor W2When the internal parameter b of (2) is 0.2, x1-x3Phase diagram on a plane.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
The invention provides a double-memristor Hopfield neural network model with coexisting multiple attractors, which is connected in a topology as follows:
the structure includes: three neurons and two memristors, as shown in fig. 1.
In the first neuron, the self-coupling connection weight of the first neuron is-1.4; the coupling connection weight of the second neuron to the first neuron is 1.2; the coupling connection weight of the third neuron to the first neuron is-7.
In the second neuron, the second neuron is not self-coupled; the coupling weight of the first neuron to the second neuron is k1W1Wherein W is1To memory resistance, k1Is the coupling strength; the coupling connection weight of the third neuron to the second neuron is 2.8.
In the third neuron, the self-coupling connection weight of the third neuron is 4; the coupling connection weight of the first neuron to the third neuron is 0.8; the coupling weight of the second neuron to the third neuron is-k2W2Wherein W is2To memory resistance, k2Is the coupling strength.
Both the memristors are non-ideal memristors based on hyperbolic functions.
The Hopfield Neural Network (HNN) may be characterized by a set of circuit state equations for n neurons. For the ith neuron, the circuit state equation is expressed as:
wherein x isiTo represent a capacitance CiState variable of the voltage across RiTo represent the resistance of the membrane resistance between the inside and outside of the neuron, IiFor input of bias current, tanh (x)j) Is a neuron activation function representing an input from a j-th neuron, and W ═ Wij) Is an n x n synaptic weight matrix representing the strength of the connection between the ith and jth neurons.
In the HNN model, the neuron activation function is a monotonic differentiable function with an upper bound and a lower bound. Therefore, a hyperbolic tangent function is generally used as a neuron activation function. When the hyperbolic non-ideal memristor represented by the following formula (2) replaces the resistive coupling amount of the connection, a memristor-based HNN can be easily constructed.
Wherein W (Φ) ═ 1-atanh (Φ). Only HNNs containing three neurons are considered in this example.
Corresponding to the connection topology shown in fig. 1, the connection matrix considered has the following form:
suppose n is 3, Ci=1、Ri=1、I i0 and RC 1. An autonomous ordinary differential equation in a dimensionless form describing the memristive network may be derived as:
wherein k represents the coupling strength of the hyperbolic memristor, and a and b are memristors W1And memory resistance W2The parameters k, a, b are all constants. Therefore, a dual memristive HNN with co-existing multiple attractors can be modeled by equation (4) above, which is a five-dimensional autonomous non-linear dynamical system.
Numerical simulation: selecting initial conditions of 5 state variables as (0, 10-9, 0, 0, 0), (0, 10-9, 0.1, 0, 0) and (0, 10-9, 0.2, 0, 0), and setting coupling strength k1=1、k 22, and respectively store the memristor W2Is set to 0.2, in the region [ -0.2, 0.3]Internal regulation memristor W1And internal parameter a of, and memristor W1Is set to 0.1, in the region [ -0.2, 0.3 [ - ]]Internal regulation memristor W2The internal parameter b of (a) can reveal the coexistence behavior of multiple attractors of the double-memristive HNN through bifurcation and phase-track diagrams.
When memory resistance W2Is set to 0.2, in the region [ -0.2, 0.3]Internal regulation memristor W1With the state variable x1The branch diagram of (A) is shown in FIG. 2, and the memory resistance W is taken1When the internal parameter a is-0.1835, at x1-x3There are three different types of attractor coexistence behaviors on the plane, as shown in fig. 3 (a); memory resistance W1When the internal parameter a of (2) is 0.15, x is1-x3The coexistence behavior of the chaotic attractors and the cycle-limit loop exists on the plane, as shown in fig. 3 (b);
when memory resistance W1Is set to 0.1, in the region [ -0.2, 0.3 [ - ]]Internal regulation memristor W2Internal parameter b, dependent on the state variable x1The branch diagram of (A) is as shown in FIG. 2(b), and the memristor W is taken2When the internal parameter b is-0.15, at x1-x3The coexistence behavior of periodic attractors with two different periods on the plane is shown in fig. 4 (a); memory resistance W20.2 in x1-x3The coexistence behavior of the chaotic attractors and the periodic two-limit loop exists on the plane, as shown in fig. 4 (b).
Therefore, the invention constructs a double-memristor Hopfield neural network model with coexisting multiple attractors.
The limitation of the protection scope of the present invention is understood by those skilled in the art, and various modifications or changes which can be made by those skilled in the art without inventive efforts based on the technical solution of the present invention are still within the protection scope of the present invention.
Claims (2)
1. A double-memristor Hopfield neural network model with coexisting multiple attractors is characterized in that: the double-memristor Hopfield neural network model is constructed by introducing two memristors into a three-neuron Hopfield neural network and simulating biological synapses by using the memristors; by changing the initial value of the state variable in the model, different types of multi-attractor coexistence phenomena are shown under different internal parameters of the memristor, so that complex dynamic behaviors in the brain are simulated.
2. The dual memristive Hopfield neural network model with co-existing multi-attractors, as in claim 1, wherein: the double-memristor Hopfield neural network model comprises a three-neuron memristor Hopfield neural network model and two non-ideal hyperbolic memristor models.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811127495.9A CN110956250A (en) | 2018-09-27 | 2018-09-27 | Double-memristor Hopfield neural network model with coexisting multiple attractors |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811127495.9A CN110956250A (en) | 2018-09-27 | 2018-09-27 | Double-memristor Hopfield neural network model with coexisting multiple attractors |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110956250A true CN110956250A (en) | 2020-04-03 |
Family
ID=69967751
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811127495.9A Pending CN110956250A (en) | 2018-09-27 | 2018-09-27 | Double-memristor Hopfield neural network model with coexisting multiple attractors |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110956250A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111814973A (en) * | 2020-07-18 | 2020-10-23 | 福州大学 | Memory computing system suitable for neural ordinary differential equation network computing |
CN112329365A (en) * | 2020-10-20 | 2021-02-05 | 安顺学院 | Coupled dual-memristor high-dimensional hidden signal generation system |
CN113379044A (en) * | 2021-05-21 | 2021-09-10 | 长沙理工大学 | Hopfield neural network system based on electromagnetic radiation effect, processor chip and terminal |
CN114936626A (en) * | 2022-05-19 | 2022-08-23 | 常州大学 | Initial value control method for discrete neuron network |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573238A (en) * | 2015-01-09 | 2015-04-29 | 江西理工大学 | Circuit design method for memory resisting cell neural network |
US20150269483A1 (en) * | 2014-03-18 | 2015-09-24 | Panasonic Intellectual Property Management Co., Ltd. | Neural network circuit and learning method for neural network circuit |
CN106779059A (en) * | 2016-12-30 | 2017-05-31 | 华中科技大学 | A kind of Circuit of Artificial Neural Networks of the Pavlov associative memory based on memristor |
CN107784359A (en) * | 2017-09-19 | 2018-03-09 | 常州大学 | A kind of more stable state oscillation circuits based on Hopfield neutral nets |
-
2018
- 2018-09-27 CN CN201811127495.9A patent/CN110956250A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150269483A1 (en) * | 2014-03-18 | 2015-09-24 | Panasonic Intellectual Property Management Co., Ltd. | Neural network circuit and learning method for neural network circuit |
CN104573238A (en) * | 2015-01-09 | 2015-04-29 | 江西理工大学 | Circuit design method for memory resisting cell neural network |
CN106779059A (en) * | 2016-12-30 | 2017-05-31 | 华中科技大学 | A kind of Circuit of Artificial Neural Networks of the Pavlov associative memory based on memristor |
CN107784359A (en) * | 2017-09-19 | 2018-03-09 | 常州大学 | A kind of more stable state oscillation circuits based on Hopfield neutral nets |
Non-Patent Citations (3)
Title |
---|
BOCHENG BAO ET AL.: ""Coexisting Behaviors of Asymmetric Attractors in Hyperbolic-Type Memristor based Hopfield Neural Network"", 《COMPUTATIONAL NEUROSCIENCE》 * |
BOCHENG BAO ET AL.: ""Two-memristor-based Chua’s hyperchaotic circuit with plane equilibrium and its extreme multistability"", 《NONLINEAR DYNAMICS》 * |
包伯成等: ""含两个忆阻器混沌电路的动力学分析"", 《中国科学:技术科学》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111814973A (en) * | 2020-07-18 | 2020-10-23 | 福州大学 | Memory computing system suitable for neural ordinary differential equation network computing |
CN111814973B (en) * | 2020-07-18 | 2022-06-21 | 福州大学 | Memory computing system suitable for neural ordinary differential equation network computing |
CN112329365A (en) * | 2020-10-20 | 2021-02-05 | 安顺学院 | Coupled dual-memristor high-dimensional hidden signal generation system |
CN112329365B (en) * | 2020-10-20 | 2022-09-09 | 安顺学院 | Coupled dual-memristor high-dimensional hidden signal generation system |
CN113379044A (en) * | 2021-05-21 | 2021-09-10 | 长沙理工大学 | Hopfield neural network system based on electromagnetic radiation effect, processor chip and terminal |
CN114936626A (en) * | 2022-05-19 | 2022-08-23 | 常州大学 | Initial value control method for discrete neuron network |
CN114936626B (en) * | 2022-05-19 | 2023-10-27 | 常州大学 | Initial value control method for discrete neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110956250A (en) | Double-memristor Hopfield neural network model with coexisting multiple attractors | |
Abdurahman et al. | Finite-time synchronization for memristor-based neural networks with time-varying delays | |
Pillai et al. | Symmetry breaking in space-time hierarchies shapes brain dynamics and behavior | |
Papageorgiou et al. | Fuzzy cognitive map learning based on nonlinear Hebbian rule | |
Carvalho | On the semantics and the use of fuzzy cognitive maps in social sciences | |
Bartfai | An ART-based modular architecture for learning hierarchical clusterings | |
Merrikh-Bayat et al. | The neuro-fuzzy computing system with the capacity of implementation on a memristor crossbar and optimization-free hardware training | |
Zhang et al. | Hmsnn: hippocampus inspired memory spiking neural network | |
CN115755621A (en) | Finite time self-adaptive synchronous control method of memristor recurrent neural network | |
Kozlova et al. | The use of neural networks for planning the behavior of complex systems | |
Scofield | Learning internal representations in the coulomb energy network | |
Ballini et al. | Learning in recurrent, hybrid neurofuzzy networks | |
JP6974955B2 (en) | Crossbar structure and optimization problem solution search system | |
Amirsoleimani et al. | STDP-based unsupervised learning of memristive spiking neural network by Morris-Lecar model | |
Toussaint | Learning a world model and planning with a self-organizing, dynamic neural system | |
Feldman | Energy and the behavior of connectionist models | |
Aparicio et al. | Why are neural networks relevant to higher cognitive function? | |
Kendall | A gradient estimator for time-varying electrical networks with non-linear dissipation | |
Hakimzadeh et al. | Interpretable Reinforcement Learning Inspired by Piaget's Theory of Cognitive Development | |
Greer | New ideas for brain modelling | |
Hasebrook et al. | Knowledge robots for knowledge workers: Self-learning agents connecting information and skills | |
Yamazaki et al. | Complexity of bird song caused by adversarial imitation learning | |
Mobahi et al. | Concept oriented imitation towards verbal human-robot interaction | |
Liu et al. | Evolution properties of complex-valued memristive differential-algebraic neural networks | |
International Neural Network Society (INNS), the IEEE Neural Network Council Cooperating Societies et al. | Brain building with GenNets |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |