no code implementations • 9 Dec 2019 • Itay Mosafi, Eli David, Nathan S. Netanyahu
The best way to extract or steal knowledge from such networks is by querying them using a large dataset of random samples and recording their output, followed by training a student network to mimic these outputs, without making any assumption about the original networks.
no code implementations • 24 Nov 2019 • Itay Mosafi, Eli David, Nathan S. Netanyahu
In addition, the time required for training the student model to reach the mentor's performance level is shorter, as a result of a simplified architecture and more available data.
