Search International and National Patent Collections

1. (WO2017156547) STRUCTURE LEARNING IN CONVOLUTIONAL NEURAL NETWORKS

Pub. No.:    WO/2017/156547    International Application No.:    PCT/US2017/022206
Publication Date: Fri Sep 15 01:59:59 CEST 2017 International Filing Date: Tue Mar 14 00:59:59 CET 2017
IPC: G06N 3/02
Applicants: MAGIC LEAP, INC.
Inventors: RABINOVICH, Andrew
BADRINARAYANAN, Vijay
DETONE, Daniel
RAJENDRAN, Srivignesh
LEE, Douglas, Bertram
MALISIEWICZ, Tomasz, J.
Title: STRUCTURE LEARNING IN CONVOLUTIONAL NEURAL NETWORKS
Abstract:
The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.