Filters








447 Hits in 1.4 sec

A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control

Zhekang Dong, Shukai Duan, Xiaofang Hu, Lidan Wang, Hai Li
2014 The Scientific World Journal  
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account  ...  Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation  ...  The Memristive Multilayer Feedforward Small-World Neural Network The Multilayer Feedforward Small-World Neural Network.  ... 
doi:10.1155/2014/394828 pmid:25202723 pmcid:PMC4150482 fatcat:lbugwptktfa6njjaxfzwczle6y

Evolution of Plastic Learning in Spiking Networks via Memristive Connections

Gerard Howard, Ella Gale, Larry Bull, Ben de Lacy Costello, Andy Adamatzky
2012 IEEE Transactions on Evolutionary Computation  
reward scenarios, and that mixtures of memristive elements provide performance advantages when compared to homogeneous memristive networks.  ...  of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time.  ...  A survey of various methods for evolving both weights and architectures in neural networks is presented in [20] .  ... 
doi:10.1109/tevc.2011.2170199 fatcat:hcg67hxrr5e45ltxkpkbdnflii

Brain‐Inspired Structural Plasticity through Reweighting and Rewiring in Multi‐Terminal Self‐Organizing Memristive Nanowire Networks

Gianluca Milano, Giacomo Pedretti, Matteo Fretto, Luca Boarino, Fabio Benfenati, Daniele Ielmini, Ilia Valov, Carlo Ricciardi
2020 Advanced Intelligent Systems  
networks. [3] With the aim of emulating brain-inspired computing paradigms, neuromorphic functionalities have been implemented in artificial neural networks based on memristive device which functionalities  ...  Current memristive crossbar architectures demonstrate the implementation of neuromorphic computing paradigms, although they are unable to emulate typical features of biological neural networks such as  ...  In contrast to conventional neural networks realized with a top-down approach based on memristive devices or transistors, these biologically inspired systems allow a low-cost realization of neural networks  ... 
doi:10.1002/aisy.202080071 fatcat:74yhl65etbarvf4thhuj5xlwue

Brain‐Inspired Structural Plasticity through Reweighting and Rewiring in Multi‐Terminal Self‐Organizing Memristive Nanowire Networks

Gianluca Milano, Giacomo Pedretti, Matteo Fretto, Luca Boarino, Fabio Benfenati, Daniele Ielmini, Ilia Valov, Carlo Ricciardi
2020 Advanced Intelligent Systems  
networks. [3] With the aim of emulating brain-inspired computing paradigms, neuromorphic functionalities have been implemented in artificial neural networks based on memristive device which functionalities  ...  Current memristive crossbar architectures demonstrate the implementation of neuromorphic computing paradigms, although they are unable to emulate typical features of biological neural networks such as  ...  In contrast to conventional neural networks realized with a top-down approach based on memristive devices or transistors, these biologically inspired systems allow a low-cost realization of neural networks  ... 
doi:10.1002/aisy.202000096 fatcat:p6fzjq54ivhpnfdsurilaagqeu

Simulation of memristive synapses and neuromorphic computing on a quantum computer [article]

Ying Li
2020 arXiv   pre-print
We also propose a three-layer neural network with the capability of universal quantum computing. Quantum state classification on the memristive neural network is demonstrated.  ...  We propose unitary quantum gates that exhibit memristive behaviours, including Ohm's law, pinched hysteresis loop and synaptic plasticity.  ...  In the memristive gate, the resistance state evolves driven by the current qubit.  ... 
arXiv:2007.09574v1 fatcat:kjjbsvcu7jhrxpimvn4kpyrclq

Integration and co-design of memristive devices and algorithms for artificial intelligence

Wei Wang, Wenhao Song, Peng Yao, Yang Li, Joseph Van Nostrand, Qinru Qiu, Daniele Ielmini, J. Joshua Yang
2020 iScience  
Memristive devices share remarkable similarities to biological synapses, dendrites, and neurons at both the physical mechanism level and unit functionality level, making the memristive approach to neuromorphic  ...  Such co-design and optimization have been the main focus of memristive neuromorphic engineering, which often abandons the "non-ideal" behaviors of memristive devices, although many of them resemble what  ...  Co-design between memristive hardware and neural network algorithms is critical for developing such brain-like neural networks.  ... 
doi:10.1016/j.isci.2020.101809 pmid:33305176 pmcid:PMC7718163 fatcat:bibhecux2nafzjexaklossadae

Table of contents

2021 IEEE Transactions on Neural Networks and Learning Systems  
Global Exponential Synchronization of Coupled Delayed Memristive Neural Networks With Reaction-Diffusion Terms via Distributed Pinning Controls .........................................................  ...  Vamvoudakis Evolving Deep Neural Networks via Cooperative Coevolution With Backpropagation ..................................... ........................................................................  ... 
doi:10.1109/tnnls.2020.3043901 fatcat:rxu6bx4dh5ezjbcr6yhzutjjgi

A Fully Memristive Spiking Neural Network with Unsupervised Learning [article]

Peng Zhou, Dong-Uk Choi, Jason K. Eshraghian, Sung-Mo Kang
2022 arXiv   pre-print
We present a fully memristive spiking neural network (MSNN) consisting of physically-realizable memristive neurons and memristive synapses to implement an unsupervised Spiking Time Dependent Plasticity  ...  The system is fully memristive in that both neuronal and synaptic dynamics can be realized by using memristors.  ...  Much of the prior work on memristive spiking neural networks (MSNNs) is constrained to using either memristive synapses or memristive neurons.  ... 
arXiv:2203.01416v2 fatcat:7zxc4ghhgveh3mfjvlc5tbtuoa

Learning Behavior of Memristor-Based Neuromorphic Circuits in the Presence of Radiation

Sumedha Gandharava Dahl, Robert C. Ivans, Kurtis D. Cantley
2019 Proceedings of the International Conference on Neuromorphic Systems - ICONS '19  
In this paper, a feed-forward spiking neural network with memristive synapses is designed to learn a spatio-temporal pattern representing the 25-pixel character 'B' by separating correlated and uncorrelated  ...  The network uses a many-to-one topology with 25 pre-synaptic neurons (afferent) each connected to a memristive synapse and one postsynaptic neuron.  ...  INTRODUCTION Neuromorphic circuits or artificial neural networks are systems inspired by biological neural networks such as the brain.  ... 
doi:10.1145/3354265.3354272 dblp:conf/icons2/DahlIC19 fatcat:k7bmt6uxo5gzrnuxj3co3hbzke

Self-organizing memristive nanowire networks with structural plasticity emulate biological neuronal circuits [article]

Gianluca Milano , Luca Boarino, Ilia Valov Department of Applied Science and Technology, Politecnico di Torino, Torino, Italy, Advanced Materials Metrology and Life Science Division, INRiM (Istituto Nazionale di Ricerca Metrologica), Torino, Italy, Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano (+9 others)
2019 arXiv   pre-print
Acting as artificial synapses, two-terminal memristive devices are considered fundamental building blocks for the realization of artificial neural networks.  ...  The operation principle of this system is based on the mutual electrochemical interaction among memristive NWs and NW junctions composing the network and regulating its connectivity depending on the input  ...  In contrast to conventional neural networks realized with a top-down approach based on memristive devices or transistors, these biologically inspired systems allow a low-cost realization of neural networks  ... 
arXiv:1909.02438v1 fatcat:terj47rb7vburiechaoguho4cm

Automating Analogue AI Chip Design with Genetic Search

Olga Krestinskaya, Khaled N. Salama, Alex P. James
2020 Advanced Intelligent Systems  
The AI applications demand accelerated computing of deep neural networks and require device miniaturization to increase chip density.  ...  The classical software-based approaches for hyperparameter optimization of the deep neural network are a resourceconsuming and complicated task.  ...  for ideal neural network and memristive crossbar-based neural network with nonidealities for a) MNIST database and b) Fashion-MNIST database. c) Comparison of average generation accuracy for ideal neural  ... 
doi:10.1002/aisy.202000075 fatcat:3hnp4lwc65ahffnr76cxbzh2le

Approximate programming of magnetic memory elements for energy saving

N. Locatelli, A.F. Vincent, S. Galdin-Retailleau, J-o. Klein, D. Querlioz
2015 2015 International Conference on Memristive Systems (MEMRISYS)  
This very low energy regime can be implemented to achieve memristive synapses with stochastic plasticity in hardware neural network [3, 4] .  ...  Hardware neural network architecture with STT-MTJs as stochastic synapses.  ... 
doi:10.1109/memrisys.2015.7378400 fatcat:melhxqwehfce5h4ifcksgigese

Non-linear Memristive Synaptic Dynamics for Efficient Unsupervised Learning in Spiking Neural Networks

Stefano Brivio, Denys R. B. Ly, Elisa Vianello, Sabina Spiga
2021 Frontiers in Neuroscience  
Spiking neural networks (SNNs) are a computational tool in which the information is coded into spikes, as in some parts of the brain, differently from conventional neural networks (NNs) that compute over  ...  We quantitatively analyze the impact of resolution and non-linearity properties of the synapses on the network training and classification performance.  ...  A comprehensive review about neural networks and spiking neural networks including also memristive devices can be found in Bouvieret al. (2019) .  ... 
doi:10.3389/fnins.2021.580909 pmid:33633531 pmcid:PMC7901913 fatcat:svcgquk6uzb7bkolf345hwqd7q

Effects of memristive synapse radiation interactions on learning in spiking neural networks

Sumedha Gandharava Dahl, Robert C. Ivans, Kurtis D. Cantley
2021 SN Applied Sciences  
AbstractThis study uses advanced modeling and simulation to explore the effects of external events such as radiation interactions on the synaptic devices in an electronic spiking neural network.  ...  Memristive synapses based on a TiO2 non-linear drift model designed in Verilog-A are utilized, with STDP learning behavior achieved through bi-phasic pre- and post-synaptic action potentials.  ...  Neural network topology Neural networks in this study have three basic components: pre-synaptic neurons, post-synaptic neurons, and memristive synapses connecting afferents to the output layer.  ... 
doi:10.1007/s42452-021-04553-0 fatcat:6sga27ul7jfdjbeep2n7ybqypm

Towards Hardware Optimal Neural Network Selection with Multi-Objective Genetic Search

O. Krestinskaya, K. Salama, A. P. James
2020 2020 IEEE International Symposium on Circuits and Systems (ISCAS)  
The selection of hyperparameters and circuit components for optimum hardware implementation of a neural network is a challenging task, which has not been automated yet.  ...  This work proposes the method for the selection of optimum neural network architecture and hyperparameters using genetic algorithm based on the hardware-related performance metrics, such an on-chip area  ...  METHODOLOGY AND RESULTS 1) Methodology: In this work, we focus on the hyperparameter optimization for analog memristive neural network implementations.  ... 
doi:10.1109/iscas45731.2020.9180514 fatcat:la5zs45nqjfdfisab7llgojkcq
« Previous Showing results 1 — 15 out of 447 results