activity
20162026
most citedBinarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

2.2k citations · 5.3k across the 18 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

cs.LG2018★ 197 cited

Scalable Methods for 8-bit Training of Neural Networks

Ron Banner, Itay Hubara, Elad Hoffer +1

Quantized Neural Networks (QNNs) are often used to improve network efficiency during the inference phase, i.e. after the network has been trained. Extensive research in the field s…

cs.LG2018★ 12 cited

Fix your classifier: the marginal value of training the last weight layer

Elad Hoffer, Itay Hubara, Daniel Soudry

Neural networks are commonly used as models for classification for a wide variety of tasks. Typically, a learned affine transformation is placed at the end of such models, yielding…