Chaotic dynamical system of Hopfield neural network influenced by neuron activation threshold and its image encryption
In the field of artificial neural networks, researchers often use the hyperbolic tangent function
as an activation function to imitate the firing rules of biological neurons and to add nonlinear …
as an activation function to imitate the firing rules of biological neurons and to add nonlinear …
Dynamics analysis and FPGA implementation of discrete memristive cellular neural network with heterogeneous activation functions
The activation function, as an important component of artificial neural networks, endows
neural networks with rich dynamical phenomena by virtue of its nonlinear properties …
neural networks with rich dynamical phenomena by virtue of its nonlinear properties …
Memristor-based circuit design of episodic memory neural network and its application in hurricane category prediction
Q Wan, J Liu, T Liu, K Sun, P Qin - Neural Networks, 2024 - Elsevier
Episodic memory, as a type of long-term memory (LTM), is used to learn and store the
unique personal experience. Based on the episodic memory biological mechanism, this …
unique personal experience. Based on the episodic memory biological mechanism, this …
Memristive Tabu learning neuron generated multi-wing attractor with FPGA implementation and application in encryption
Memristors, with their unique nonlinear characteristics, are highly suitable for construction
novel neural models with rich dynamic behaviors. In this paper, a memristor with piecewise …
novel neural models with rich dynamic behaviors. In this paper, a memristor with piecewise …
Dynamic analysis and hardware implementation of multi-scroll Hopfield neural networks with three different memristor synapses
F Yu, C Wu, Y Lin, S He, W Yao, S Cai, J Jin - Nonlinear Dynamics, 2024 - Springer
Neurons play an important role in forming behaviors and cognition through synaptic
interactions. When organized into neural networks, these neurons can exhibit complex …
interactions. When organized into neural networks, these neurons can exhibit complex …
A universal discrete memristor with application to multi-attractor generation
S Zhang, Y Li, D Lu, X Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Discrete memristors have been employed in discrete maps for the purpose of chaos
generation and regulation. In this paper, a novel universal model for discrete memristors is …
generation and regulation. In this paper, a novel universal model for discrete memristors is …
A novel memristive synapse-coupled ring neural network with countless attractors and its application
This paper presents a novel memristive synapse-coupled ring neural network (MSCRNN)
through introducing a nonvolatile memristor into a three-neuron Hopfield neural network …
through introducing a nonvolatile memristor into a three-neuron Hopfield neural network …
Memristive PAD three-dimensional emotion generation system based on D–S evidence theory
In this work, a Pleasure–Arousal–Dominance (PAD) three-dimensional brain-like emotion
generation system is proposed by simulating the brain tissue structures involved in emotion …
generation system is proposed by simulating the brain tissue structures involved in emotion …
Multiple dynamics and Hamilton energy analysis of a simple chaotic and hyperchaotic 3D non-autonomous circuit
Y Zhang, Y Li - Chaos, Solitons & Fractals, 2024 - Elsevier
A structurally simple chaotic and hyperchaotic 3D non-autonomous circuit is presented,
which incorporates three dynamic components, an inductor, a capacitor, and an active first …
which incorporates three dynamic components, an inductor, a capacitor, and an active first …
Memristor-Based Attention Network for Online Real-Time Object Tracking
Most existing visual object tracking approaches are implemented based on von Neumann
computation systems, which inevitably have the problems of high latency. Additionally …
computation systems, which inevitably have the problems of high latency. Additionally …