10 citations · 21 across the 5 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cs.LG2016★ 2 cited
Deep Learning with Eigenvalue Decay Regularizer
Oswaldo Ludwig
This paper extends our previous work on regularization of neural networks using Eigenvalue Decay by employing a soft approximation of the dominant eigenvalue in order to enable the…
cs.CL2016★ 10 cited
Deep Embedding for Spatial Role Labeling
Oswaldo Ludwig, Xiao Liu, Parisa Kordjamshidi +1
This paper introduces the visually informed embedding of word (VIEW), a continuous vector representation for a word extracted from a deep neural model trained using the Microsoft C…