Deep Learning 自学

Deep Learning 介绍

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence.

Deep Learning 动机

Deep Learning

--主要用于NLP（自然语言处理），可用于情感分析

--算法库（Python）

--Deep Belief Networks（revolutionary work）：Hinton的PPT

--RestrictedBoltzmann Machine

1. Greedy Layer-Wise Training of Deep Networks
2. A fast learning algorithm for deep belief nets
3. Efficient Learning of Sparse Representations with an Energy-Based Model

把learning hierarchy 看做一个network，三个paper都有的特征
①无监督学习用于每一层网络的pre-train；
②每次用无监督学习只训练一层，将其训练结果作为其higher一层的输入；
③用监督学习去调整所有层

Local Generalization