Authors
Sudheendra Vijayanarasimhan, Jonathon Shlens, Rajat Monga, Jay Yagnik
Publication date
2014/12/23
Journal
arXiv preprint arXiv:1412.7479
Description
Abstract: Deep neural networks have been extremely successful at various image, speech,
video recognition tasks because of their ability to model deep structures within the data.
However, they are still prohibitively expensive to train and apply for problems containing
millions of classes in the output layer. Based on the observation that the key computation
common to most neural network layers is a vector/matrix product, we propose a fast locality-
sensitive hashing technique to approximate the actual dot product enabling us to scale up ...
Total citations
2015201642
Scholar articles
S Vijayanarasimhan, J Shlens, R Monga, J Yagnik - arXiv preprint arXiv:1412.7479, 2014