1) polynomial neural network
多项式神经网络
1.
This paper proposed a new face detection method based on independent component analysis(ICA)and polynomial neural network(PNN).
自动人脸检测是人脸识别系统的一个重要部分,本文提出了一种新的基于独立成分分析(ICA)和多项式神经网络(PNN)相结合的人脸检测方法,该方法首先在训练样本中使用ICA分离出代表人脸和非人脸特征子空间的独立影像基,把训练图像映射到该子空间降维后作为PNN网络的输入训练网络;对测试图像采用移动多尺度窗口提取图像模式,采用ICA降维后输入PNN网络,进而分类检测出人脸和非人脸。
2) polynomial feedforward artificial neural network
多项式前向神经网络
3) distributed multi-subnet neural networks
分布式多子网神经网络
1.
Based on the feature of the sensitivity detection of catalytic sensor to inflammble different gas,single catalytic sensor is used to analyze mixed-inflammable gases with unknown components by distributed multi-subnet neural networks in different electric field.
根据催化传感器在不同的电场条件下具有不同气体检测灵敏度的特点,介绍了采用单一的热催化传感器在不同的电场强度下,通过分布式多子网神经网络对含未知气体的可燃混合气体进行分析的新方法。
4) multiple neural network
多神经网络
1.
Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors.
本文提出了一种用多神经网络建立动态软测量模型的通用方法 。
2.
The approach to build software sensor model by multiple neural networks (MNN) based on Kmeans clustering method is presented.
采用多神经网络结构建立软测量模型。
5) multiple neural networks
多神经网络
1.
The application of multiple neural networks in building software instrument;
多神经网络在软测量仪表中的应用
2.
A new software sensor model based on multiple neural networks(MNN)is presented in this paper.
该文采用多神经网络模型方法,充分利用尽可能得到的可在线测量信息,可有效地提高模型的估计精度和鲁棒性。
3.
Aiming at early stage latent faults of EHV large capacity transformers,a new fault diagnosis method based on mathematical morphology combined with multiple neural networks is presented.
针对超高压、大容量电力变压器的早期潜伏性故障,提出了一种基于数学形态学融合多神经网络的故障诊断新方法。
6) Polynomial neural networks
多项式网络
补充资料：多项式乘多项式法则
Image:1173836820929048.jpg
多项式乘多项式法则
先用一个多项式的每一项乘以另一个多项式的每一项，再把所得的积相加。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。