BP神经网络

来源:百度文库 编辑:神马文学网 时间:2024/04/29 17:50:55

      BP(Back Propagation)网络是1986年由Rumelhart和McCelland为首的科学家小组提出,是一种按误差逆传播算法训练的多层前馈网络,是目前应用最广泛的神经网络模型之一。BP网络能学习和存贮大量的输入-输出模式映射关系,而无需事前揭示描述这种映射关系的数学方程。它的学习规则是使用最速下降法,通过反向传播来不断调整网络的权值和阈值,使网络的误差平方和最小。BP神经网络模型拓扑结构包括输入层(input)、隐层(hide layer)和输出层(output layer)。

Neural Network Toolbox

Design and simulate neural networks


Neural Network Toolbox™ provides tools for designing, implementing, visualizing, and simulating neural networks. Neural networks are used for applications where formal analysis would be difficult or impossible, such as pattern recognition and nonlinear system identification and control. Neural Network Toolbox supports feedforward networks, radial basis networks, dynamic networks, self-organizing maps, and other proven network paradigms.


 

  View data sheet (499k) FREE Product
Technical Kit



  • New Product Demonstration: Introduction to the Neural Network
  • MATLAB based book by the authors of the Neural Network Toolbox: "Neural Network Design"
  • Neural network design course offered via distance learning