📌  相关文章
📜  PyBrain-使用前馈网络

📅  最后修改于: 2020-12-10 05:16:33             🧑  作者: Mango

前馈网络是一个神经网络，其中节点之间的信息沿向前方向移动，并且永远不会向后传播。前馈网络是人工神经网络中可用的网络中的第一个和最简单的网络。信息从输入节点传递到隐藏节点之后，再传递到输出节点。

在本章中，我们将讨论如何-

  • 创建前馈网络
  • 将连接和模块添加到FFN

创建前馈网络

您可以使用自己选择的Python IDE，即PyCharm。在此，我们使用Visual Studio Code编写代码，并将在终端中执行相同的代码。

要创建前馈网络，我们需要从pybrain.structure导入它，如下所示-

ffn.py

from pybrain.structure import FeedForwardNetwork
network = FeedForwardNetwork()
print(network)

执行如下所示的ffn.py-

C:\pybrain\pybrain\src>python ffn.py
FeedForwardNetwork-0
Modules:
[]
Connections:
[]

我们尚未向前馈网络添加任何模块和连接。因此，网络显示模块和连接的空数组。

添加模块和连接

首先，我们将创建输入，隐藏，输出层，并将其添加到模块中，如下所示：

ffy.py

from pybrain.structure import FeedForwardNetwork
from pybrain.structure import LinearLayer, SigmoidLayer
network = FeedForwardNetwork()

#creating layer for input => 2 , hidden=> 3 and output=>1
inputLayer = LinearLayer(2)
hiddenLayer = SigmoidLayer(3)
outputLayer = LinearLayer(1)

#adding the layer to feedforward network
network.addInputModule(inputLayer)
network.addModule(hiddenLayer)
network.addOutputModule(outputLayer)

print(network)

输出

C:\pybrain\pybrain\src>python ffn.py
FeedForwardNetwork-3
Modules:
[]
Connections:
[]

我们仍然使模块和连接为空。我们需要提供与创建的模块的连接，如下所示：

这是我们在输入，隐藏和输出层之间创建连接并将代码添加到网络的代码。

ffy.py

from pybrain.structure import FeedForwardNetwork
from pybrain.structure import LinearLayer, SigmoidLayer
from pybrain.structure import FullConnection
network = FeedForwardNetwork()

#creating layer for input => 2 , hidden=> 3 and output=>1
inputLayer = LinearLayer(2)
hiddenLayer = SigmoidLayer(3)
outputLayer = LinearLayer(1)

#adding the layer to feedforward network
network.addInputModule(inputLayer)
network.addModule(hiddenLayer)
network.addOutputModule(outputLayer)

#Create connection between input ,hidden and output
input_to_hidden = FullConnection(inputLayer, hiddenLayer)
hidden_to_output = FullConnection(hiddenLayer, outputLayer)

#add connection to the network
network.addConnection(input_to_hidden)
network.addConnection(hidden_to_output)

print(network)

输出

C:\pybrain\pybrain\src>python ffn.py
FeedForwardNetwork-3
Modules:
[]
Connections:
[]

我们仍然无法获得模块和连接。现在让我们添加最后一步，即，我们需要添加sortModules()方法，如下所示：

ffy.py

from pybrain.structure import FeedForwardNetwork
from pybrain.structure import LinearLayer, SigmoidLayer
from pybrain.structure import FullConnection
network = FeedForwardNetwork()

#creating layer for input => 2 , hidden=> 3 and output=>1
inputLayer = LinearLayer(2)
hiddenLayer = SigmoidLayer(3)
outputLayer = LinearLayer(1)

#adding the layer to feedforward network
network.addInputModule(inputLayer)
network.addModule(hiddenLayer)
network.addOutputModule(outputLayer)

#Create connection between input ,hidden and output
input_to_hidden = FullConnection(inputLayer, hiddenLayer)
hidden_to_output = FullConnection(hiddenLayer, outputLayer)

#add connection to the network
network.addConnection(input_to_hidden)
network.addConnection(hidden_to_output)
network.sortModules()

print(network)

输出

C:\pybrain\pybrain\src>python ffn.py
FeedForwardNetwork-6
Modules:
[, 
   ]
Connections:
[ 'LinearLayer-8'>, 
    'SigmoidLayer-7'>]

现在，我们可以看到feedforwardnetwork的模块和连接详细信息。