Hardware elementary perceptron based on polyaniline memristive devices
Hardware elementary perceptron based on polyaniline memristive devices
复制标题
DOI：
10.1016/j.orgel.2015.06.015
复制
发表时间：
2015-10-01
影响因子：
3.2
通讯作者：
Kovalchuk, M. V.
中科院分区：
文献类型：
--
作者：
Demin, V. A.;Erokhin, V. V.;Kovalchuk, M. V.
初级感知器是一种具有单层自适应链路和一个输出神经元的人工神经网络，可以解决简单的线性可分任务，如不变模式识别、线性逼近、预测等。我们报告了使用聚苯胺基记忆器件作为模拟链路权重的初级感知器的硬件实现。以线性可分任务为例，采用误差校正算法使感知器学习NAND和NOR逻辑函数的实现。基本感知器的物理实现证明了使用有机记忆装置形成基于硬件的神经形态网络的能力。这一结果为非常紧凑、低挥发性和高性能的神经芯片的新方法提供了巨大的希望，这些神经芯片可以用于大量的智能产品和应用。(C) 2015 Elsevier B.V.版权所有
Elementary perceptron is an artificial neural network with a single layer of adaptive links and one output neuron that can solve simple linearly separable tasks such as invariant pattern recognition, linear approximation, prediction and others. We report on the hardware realization of the elementary perceptron with the use of polyaniline-based memristive devices as the analog link weights. An error correction algorithm was used to get the perceptron to learn the implementation of the NAND and NOR logic functions as examples of linearly separable tasks. The physical realization of an elementary perceptron demonstrates the ability to form the hardware-based neuromorphic networks with the use of organic memristive devices. The results provide a great promise toward new approaches for very compact, low-volatile and high-performance neurochips that could be made for a huge number of intellectual products and applications. (C) 2015 Elsevier B.V. All rights reserved.