Alias method for sampling
Sampling from multiple discrete items with diverse probability is relatively ...
The Perplexity of Neural Language Model
Given a list of word vectors: \(x_1,\cdots,x_{t-1},x_t,x_{t+1},\cdots,x_T\) ...
Hierarchical clustering
1. Hierarchical Clustering Approach A typical clustering analysis approac...
Scheduled sampling for sequence prediction with recurrent neural networks
traditional seq2seq model is trained by teacher-forcing, which is totally ...