Login / Signup
Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability.
Alberto Delmas
Sayeh Sharify
Patrick Judd
Andreas Moshovos
Published in:
CoRR (2017)
Keyphrases
</>
deep learning
fully connected
deep belief networks
restricted boltzmann machine
conditional random fields
unsupervised feature learning
scale free
machine learning
unsupervised learning
mental models
neural network
weakly supervised
higher order
probabilistic model
complex networks
small world