Skip to content
conftrace_

spherical softmax

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large sparse target (1) sparse target (1) hierarchical softmax (1) neural network (1) neural language model (1) word embedding (1) gradient updates (1) gradient descent (1) sparse prediction (1) computational efficiency (1)

Papers

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets NeurIPS 2015