PyBrain - 使用前馈网络


前馈网络是一种神经网络,节点之间的信息向前移动,永远不会向后传播。前馈网络是人工神经网络中第一个也是最简单的网络。信息从输入节点传递到隐藏节点,然后传递到输出节点。

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

您可以使用您选择的 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.struct导入它,如下所示 -

ffn.py

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

执行 ffn.py 如下所示 -

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,我们将创建输入层、隐藏层、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:
[]

我们仍然将模块和连接视为空。我们需要提供与创建的模块的连接,如下所示 -

在下面的代码中,我们创建了输入层、隐藏层和输出层之间的连接,并将该连接添加到网络中。

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:
[<LinearLayer 'LinearLayer-3'gt;, <SigmoidLayer 'SigmoidLayer-7'>, 
   <LinearLayer 'LinearLayer-8'>]
Connections:
[<FullConnection 'FullConnection-4': 'SigmoidLayer-7' -> 'LinearLayer-8'>, 
   <FullConnection 'FullConnection-5': 'LinearLayer-3' -> 'SigmoidLayer-7'>]

我们现在可以看到前馈网络的模块和连接详细信息。