Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning

Most conventional memristor-based Pavlov associative memory neural network circuits have been working on realizing the learning and forgetting functions of simultaneous conditioning. However, the time interval between unconditional stimulus and conditional stimulus is a critical variable in classica...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xinyu Xu, Weilin Xu, Baolin Wei, Fangrong Hu
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/f89da722d53247b0aca6d683e1d437ea
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f89da722d53247b0aca6d683e1d437ea
record_format dspace
spelling oai:doaj.org-article:f89da722d53247b0aca6d683e1d437ea2021-11-18T00:09:36ZMemristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning2169-353610.1109/ACCESS.2021.3122973https://doaj.org/article/f89da722d53247b0aca6d683e1d437ea2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9591231/https://doaj.org/toc/2169-3536Most conventional memristor-based Pavlov associative memory neural network circuits have been working on realizing the learning and forgetting functions of simultaneous conditioning. However, the time interval between unconditional stimulus and conditional stimulus is a critical variable in classical conditioning. Different unconditional and conditional stimulus intervals evoke associative memory of brains with different rates. For example, learning in simultaneous conditioning is less effective than delay conditioning. Therefore, a memristor-based neural network circuit of delay and simultaneous conditioning is designed. The proposed circuit consists of learning states detection module, voltage control module, and synapse module. Many functions, such as short-delay conditioning learning, long-delay conditioning learning, simultaneous conditioning learning, experience learning, and two types of forgetting are implemented by the circuit. In particular, the so-called experience learning is that learning the forgotten knowledge will be faster than before and learning again will forget more slowly. This function is more bionic. The correctness of the design is demonstrated through simulations using PSPICE.Xinyu XuWeilin XuBaolin WeiFangrong HuIEEEarticleAssociative memorymemristive neural network circuitmemristordelay conditioningElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148933-148947 (2021)
institution DOAJ
collection DOAJ
language EN
topic Associative memory
memristive neural network circuit
memristor
delay conditioning
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Associative memory
memristive neural network circuit
memristor
delay conditioning
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Xinyu Xu
Weilin Xu
Baolin Wei
Fangrong Hu
Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning
description Most conventional memristor-based Pavlov associative memory neural network circuits have been working on realizing the learning and forgetting functions of simultaneous conditioning. However, the time interval between unconditional stimulus and conditional stimulus is a critical variable in classical conditioning. Different unconditional and conditional stimulus intervals evoke associative memory of brains with different rates. For example, learning in simultaneous conditioning is less effective than delay conditioning. Therefore, a memristor-based neural network circuit of delay and simultaneous conditioning is designed. The proposed circuit consists of learning states detection module, voltage control module, and synapse module. Many functions, such as short-delay conditioning learning, long-delay conditioning learning, simultaneous conditioning learning, experience learning, and two types of forgetting are implemented by the circuit. In particular, the so-called experience learning is that learning the forgotten knowledge will be faster than before and learning again will forget more slowly. This function is more bionic. The correctness of the design is demonstrated through simulations using PSPICE.
format article
author Xinyu Xu
Weilin Xu
Baolin Wei
Fangrong Hu
author_facet Xinyu Xu
Weilin Xu
Baolin Wei
Fangrong Hu
author_sort Xinyu Xu
title Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning
title_short Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning
title_full Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning
title_fullStr Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning
title_full_unstemmed Memristor-Based Neural Network Circuit of Delay and Simultaneous Conditioning
title_sort memristor-based neural network circuit of delay and simultaneous conditioning
publisher IEEE
publishDate 2021
url https://doaj.org/article/f89da722d53247b0aca6d683e1d437ea
work_keys_str_mv AT xinyuxu memristorbasedneuralnetworkcircuitofdelayandsimultaneousconditioning
AT weilinxu memristorbasedneuralnetworkcircuitofdelayandsimultaneousconditioning
AT baolinwei memristorbasedneuralnetworkcircuitofdelayandsimultaneousconditioning
AT fangronghu memristorbasedneuralnetworkcircuitofdelayandsimultaneousconditioning
_version_ 1718425262851358720