[原]MIT的《深度学习》精读（16）
The quintessential example of a representation learning algorithm is the autoencoder. An autoencoder is the combination of an encoder function that converts the input data into a different representation, and a decoder function that converts the new representation back into the original format. Autoencoders are trained to preserve as much information as possible when an input is run through the encoder and then the decoder, but are also trained to make the new representation have various nice properties. Different kinds of autoencoders aim to achieve different kinds of properties.
最为经典的特征值学习算法就是autoencoder编码器，它组合了一个编码器功能和一个解码器功能，编码器主要用来从原始数据转换为各种各样的特征值表示，解码器是把新的特征值转换回原来的格式表示。Autoencoder在训练的过程中，尽可能把原始数据表示的特征值提取出来，以便解码器最大化地转换回原来的表示，因此在被训练之后，它已经产生了很好的特征值表示。不同种类的autoencoder可以完成不同种类属性的特征值学习。
http://blog.csdn.net/kevin_bobolkevin/article/details/50590612
http://blog.csdn.net/changyuanchn/article/details/15681853