TY - JOUR
T1 - Offset Boosting-Oriented Construction of Multi-Scroll Attractor via a Memristor Model
AU - Li, Yongxin
AU - Li, Chunbiao
AU - Zhang, Sen
AU - Zheng, Yuanjin
AU - Chen, Guanrong
PY - 2025/2
Y1 - 2025/2
N2 - The static architecture of artificial neural networks has fixed synaptic weights, whose connections do not change according to new information or learning experience. In contrast, the capacity of synaptic weight empowers biological neural networks to learn and adapt to diverse tasks, resulting in various dynamical behaviors. In this paper, a novel memristor model is designed into the Hopfield neural network for generating any desired number of multi-scroll attractors. Offset booster provides a channel for distance regulation and number control of coexisting attractors. Independent offset boosters determine the coexisting patterns including the types of one-scroll attractor, two-scroll attractor, four-scroll attractor, and other mixed types. In addition, the digital circuit platform of CH32V307 is applied to verify numerical simulations. Finally, the chaotic data generated in the memristive Hopfield neural network is introduced into the northern goshawk optimization (MHNN-NGO), by which the full network optimization is achieved. © 2024 IEEE.
AB - The static architecture of artificial neural networks has fixed synaptic weights, whose connections do not change according to new information or learning experience. In contrast, the capacity of synaptic weight empowers biological neural networks to learn and adapt to diverse tasks, resulting in various dynamical behaviors. In this paper, a novel memristor model is designed into the Hopfield neural network for generating any desired number of multi-scroll attractors. Offset booster provides a channel for distance regulation and number control of coexisting attractors. Independent offset boosters determine the coexisting patterns including the types of one-scroll attractor, two-scroll attractor, four-scroll attractor, and other mixed types. In addition, the digital circuit platform of CH32V307 is applied to verify numerical simulations. Finally, the chaotic data generated in the memristive Hopfield neural network is introduced into the northern goshawk optimization (MHNN-NGO), by which the full network optimization is achieved. © 2024 IEEE.
KW - Hopfield neural network
KW - memristor model
KW - multi-scroll attractor
KW - Offset boosting
UR - http://www.scopus.com/inward/record.url?scp=85204773001&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85204773001&origin=recordpage
U2 - 10.1109/TCSI.2024.3455350
DO - 10.1109/TCSI.2024.3455350
M3 - RGC 21 - Publication in refereed journal
SN - 1549-8328
VL - 72
SP - 918
EP - 931
JO - IEEE Transactions on Circuits and Systems—I: Regular Papers
JF - IEEE Transactions on Circuits and Systems—I: Regular Papers
IS - 2
ER -