Search International and National Patent Collections

1. (WO2018140969) MULTI-TASK NEURAL NETWORKS WITH TASK-SPECIFIC PATHS

Pub. No.:    WO/2018/140969    International Application No.:    PCT/US2018/016024
Publication Date: Fri Aug 03 01:59:59 CEST 2018 International Filing Date: Wed Jan 31 00:59:59 CET 2018
IPC: G06N 3/08
G06N 3/04
Applicants: GOOGLE LLC
Inventors: WIERSTRA, Daniel Pieter
FERNANDO, Chrisantha, Thomas
PRITZEL, Alexander
BANARSE, Dylan, Sunil
BLUNDELL, Charles
RUSU, Andrei-Alexandru
ZWOLS, Yori
HA, David
Title: MULTI-TASK NEURAL NETWORKS WITH TASK-SPECIFIC PATHS
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using multi-task neural networks. One of the methods includes receiving a first network input and data identifying a first machine learning task to be performed on the first network input; selecting a path through the plurality of layers in a super neural network that is specific to the first machine learning task, the path specifying, for each of the layers, a proper subset of the modular neural networks in the layer that are designated as active when performing the first machine learning task; and causing the super neural network to process the first network input using (i) for each layer, the modular neural networks in the layer that are designated as active by the selected path and (ii) the set of one or more output layers corresponding to the identified first machine learning task.