Note for ML,NN,DL

note DL NN ML

A Guide to Recurrent Neural Networks and Back-propagation （2002）
a simple recurrent neural network 讲了一个很简单清楚的循环神经网络，其中还讲到BP算法如何从损失函数对参数求导中得到，循环神经网络中的BP算法
Improving Word Representations via Global Context and Multiple Word Prototypes ACL2012
We present a new neural network architecture which 1) learns word embeddings that better capture the semantics of words by incorporating both local and global document context, and 2) accounts forhomonymyandpolysemybylearningmul tiple embeddings per word