96 citations · 263 across the 8 of their papers we have counts for
Showing cs.NEShow all
2 papers · 1 filter
cs.NE2016★ 1 cited
Exact gradient updates in time independent of output size for the spherical loss family
Pascal Vincent, Alexandre de Brébisson, Xavier Bouthillier
An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models…
cs.NE2014★ 17 cited
Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
Pascal Vincent, Alexandre de Brébisson, Xavier Bouthillier
An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models…