Unsupervised Feature Learning via Non-parametric Instance Discrimination

The Noise Contrastive Estimation for softmax output written in Pytorch

Tensorflow implementation of "Representation Learning with Contrastive Predictive Coding"

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Tensorflow NCE loss in Keras

language models toolkits with hierarchical softmax setting

a pytorch version lstm language model

NCE Learning

Noise Contrastive Estimation (NCE) in PyTorch

Evaluated the word vectors learned from both nce and cross entropy loss functions using word analogy tests

📈🎓