Pybrain 简明教程
PyBrain - Introduction to PyBrain Networks
PyBrain 是为使用 Python 进行机器学习而开发的库。有许多机器学习的重要概念，其中一个是网络。网络由模块组成，它们通过连接连接。
PyBrain is a library developed for Machine Learning with Python. There are some important concepts in Machine Learning and one among them is Networks. A network is composed of modules and they are connected using connections.
简单神经网络的布局如下：
A layout of a simple neural network is as follows −
Pybrain 支持神经网络，如前馈网络、循环网络等。
Pybrain supports neural networks such as Feed-Forward Network, Recurrent Network, etc.
feed-forward network 是一个神经网络，其中节点之间的信息在正向移动，决不会往后退。在人工神经网络中，前馈网络是第一个也是最简单的一个。信息从输入节点传递到隐藏节点，然后传递到输出节点。
A feed-forward network is a neural network, where the information between nodes moves in the forward direction and will never travel backward. Feed Forward network is the first and the simplest one among the networks available in the artificial neural network. The information is passed from the input nodes, next to the hidden nodes and later to the output node.
以下是简单前馈网络布局。
Here is a simple feed forward network layout.
圆圈表示为模块而带箭头的线表示与模块的连接。
The circles are said to be modules and the lines with arrows are connections to the modules.
节点 A 、 B 、 C 和 D 是输入节点
The nodes A, B, C and D are input nodes
H1 、 H2 、 H3 、 H4 是隐藏节点，O 是输出。
H1, H2, H3, H4 are hidden nodes and O is the output.
在上述网络中，我们有 4 个输入节点、4 个隐含层和 1 个输出。该图表中显示的线数指示模型中在训练期间将调整的权重参数。
In the above network, we have 4 input nodes, 4 hidden layers and 1 output. The number of lines shown in the diagram indicate the weight parameters in the model that are adjusted during training.
Recurrent Networks 与前馈网络类似，唯一的不同之处在于它必须记住每一步的数据。必须保存每一步的历史记录。
Recurrent Networks are similar to Feed Forward Network with the only difference that it has to remember the data at each step. The history of each step has to be saved.
以下是循环网络的简单布局 −
Here is a simple Layout of Recurrent Network −
