Related Experiment Video
Updated: Jul 7, 2026
10:51
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
Published on: March 10, 2011
The hysteretic Hopfield neural network
1Signal and Image Processing Institute, Department of Electrical Engingering-Systems, University of Southern California, Los Angeles, CA 90089-2564, USA.
IEEE Transactions on Neural Networks
|February 6, 2008
Summary
A novel hysteretic neuron activation function creates a hysteretic Hopfield neural network (HHNN) for improved convergence in complex problem-solving. This new model enhances solution frequency by leveraging physical system properties.
Area of Science:
- Neuroscience
- Computational Science
- Physics
Background:
- Traditional neural networks lack mechanisms to handle complex dynamics.
- Physical systems exhibit hysteresis, a property not yet widely applied in neural network design.
Purpose of the Study:
- To introduce a new neuron activation function inspired by physical hysteresis.
- To develop and analyze a hysteretic Hopfield neural network (HHNN).
- To demonstrate the practical application and advantages of the HHNN model.
Main Methods:
- Proposed a novel neuron activation function based on hysteresis.
- Integrated this function into a fully connected dynamical system to create the HHNN.
- Developed an analog implementation, dynamical equation, and energy function for the HHNN.
- Proved Lyapunov stability for the proposed model.
- Applied the HHNN to solve the N-queen combinatorial optimization problem.
Main Results:
- Successfully developed and implemented the hysteretic Hopfield neural network (HHNN).
- Demonstrated Lyapunov stability for the HHNN model.
- Showcased the HHNN's ability to solve the N-queen problem.
- Observed an increased frequency of convergence to solutions by varying activation function parameters, highlighting the advantages of hysteresis.
Conclusions:
- The proposed hysteretic neuron activation function and the resulting HHNN offer a promising new approach in neural network design.
- Hysteresis provides a mechanism for enhanced convergence frequency in solving complex problems.
- The HHNN model shows potential for applications in combinatorial optimization and other dynamic system modeling.
Related Concept Videos
01:25Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
01:23Propagation of Action Potentials
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
01:21Neurons: The Axon
Axons are long, cytoplasmic processes of nerve cells capable of propagating electrical impulses known as action potentials. The cytoplasm or axoplasm of an axon contains neurofibrils, neurotubules, small vesicles, lysosomes, mitochondria, and various enzymes, all encased within the axolemma, the plasma membrane of the axon.
The axon attaches to the cell body at a cone-shaped elevation called the axon hillock. The initial part of the axon, closest to the hillock, is known as the initial segment.
The axon attaches to the cell body at a cone-shaped elevation called the axon hillock. The initial part of the axon, closest to the hillock, is known as the initial segment.
01:17Ampere-Maxwell's Law: Problem-Solving
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the problem,...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the problem,...
01:28Neuronal Communication
Neurons, the fundamental units of the brain and nervous system, communicate through complex electrochemical signals that underpin all cognitive and bodily functions. This communication is primarily facilitated by a process involving the generation and propagation of an action potential along the axon of the neuron. When the internal electrical charge of a neuron surpasses a certain threshold, an action potential is triggered. This rapid change in voltage travels swiftly along the axon to the...
01:26Classification of Systems-I
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as: