问题描述
我正在尝试在 Python 中创建自回归神经网络 (NARX).我只能找到一个库 PyNeurgen.但我找不到任何示例程序来使用它.使用网络训练和预测时间序列.如果有人可以分享如何使用网络训练和预测时间序列.或者如果有任何其他好的 NARX 库.
I am trying to create autoregressive neural network (NARX) in Python. I just could find one library PyNeurgen. But I am not able to find any sample program to use it. To train and predict time series using the network. If anyone can share how to train and predict time series using network. Or if there is any other good library for NARX.
推荐答案
查看教程:http://pyneurgen.sourceforge.net/tutorial_nn.html你可以在这里找到测试用例: https://github.com/katerina7479/pyneurgen/blob/22e25c01469b3967360401196e7cd12dd5b00358/pyneurgen/demo/simple_network_with_graphs.py
check the tutorial: http://pyneurgen.sourceforge.net/tutorial_nn.html and You can find testcase here: https://github.com/katerina7479/pyneurgen/blob/22e25c01469b3967360401196e7cd12dd5b00358/pyneurgen/demo/simple_network_with_graphs.py
...
from pyneurgen.recurrent import NARXRecurrent
...
# NARXRecurrent
input_nodes = 2
hidden_nodes = 2
output_nodes = 2
output_order = 3
incoming_weight_from_output = .6
input_order = 2
incoming_weight_from_input = .4
net = NeuralNet()
net.init_layers(input_nodes, [hidden_nodes], output_nodes,
NARXRecurrent(
output_order,
incoming_weight_from_output,
input_order,
incoming_weight_from_input))
net.randomize_network()
这篇关于NARX PyNeurgen 库的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持跟版网！