首页> 外文会议>International conference on artificial intelligence >Analog and Digital Modeling of a Scalable Neural Network
【24h】

Analog and Digital Modeling of a Scalable Neural Network

机译:可扩展神经网络的模拟和数字建模

获取原文

摘要

Proposed are the new types of fast training, scalable analog and digital artificial neural networks (p-networks) based on the new model of formal neuron, described in. The p-network includes synapses with a plurality of weights, and devices of weight selection based on the intensity of the incoming signal. Versions of the p-networks are presented that are formed with resistance elements, such as, memristor elements. Also described are the matrix methods of training and operation for the proposed network Training time for the new network is linearly dependent on the size of the network and the volume of data, in contrast to other models of artificial neural networks with the exponential dependence. Thus, p-network training time is dozens time faster than training time of the known networks. The obtained results can be applied in existing artificial neural networks, and in development of a neural microchip.
机译:提出了基于形式神经元的新模型的新型快速训练,可扩展的模拟和数字人工神经网络(p-networks),如所述。p网络包括具有多个权重的突触和权重选择设备根据输入信号的强度。提出了由电阻元件(例如忆阻器元件)形成的p网络版本。还介绍了所建议网络的训练和操作的矩阵方法,与其他具有指数依赖关系的人工神经网络模型相比,新网络的训练时间线性依赖于网络的大小和数据量。因此,p网络的训练时间比已知网络的训练时间快几十倍。所得结果可应用于现有的人工神经网络和神经微芯片的开发中。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号