首页> 外文期刊>Advances in Adaptive Data Analysis >AN INITIALIZATION METHOD FOR FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING POLYNOMIAL BASES
【24h】

AN INITIALIZATION METHOD FOR FEEDFORWARD ARTIFICIAL NEURAL NETWORKS USING POLYNOMIAL BASES

机译:基于多项式基的前向人工神经网络的初始化方法

获取原文
获取原文并翻译 | 示例
           

摘要

We propose an initialization method for feedforward artificial neural networks (FFANNs) trained to model physical systems. A polynomial solution of the physical system is obtained using a mathematical model and then mapped into the neural network to initialize its weights. The network can next be trained with a dataset to refine its accuracy. We focus attention on an elliptical partial differential equation modeled using a feedforward backpropagation network. We present a numerical example and compare our method with other initialization methods. Our method converges nearly 90% faster compared to random weights, with higher probability of convergence to an acceptable local minimum.
机译:我们提出了一种前馈人工神经网络(FFANNs)的初始化方法,该方法经过训练可以对物理系统进行建模。使用数学模型获得物理系统的多项式解,然后将其映射到神经网络以初始化其权重。接下来可以使用数据集训练网络以改善其准确性。我们将注意力集中在使用前馈反向传播网络建模的椭圆偏微分方程上。我们提供一个数值示例,并将我们的方法与其他初始化方法进行比较。与随机权重相比,我们的方法收敛快近90%,收敛到可接受的局部最小值的可能性更高。

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