Search International and National Patent Collections

1. (WO2018201151) NEURAL NETWORK OPTIMIZER SEARCH

Pub. No.:    WO/2018/201151    International Application No.:    PCT/US2018/030281
Publication Date: Fri Nov 02 00:59:59 CET 2018 International Filing Date: Tue May 01 01:59:59 CEST 2018
IPC: G06N 3/08
G06N 3/04
Applicants: GOOGLE LLC
Inventors: BELLO, Irwan
ZOPH, Barret
VASUDEVAN, Vijay
LE, Quoc V.
Title: NEURAL NETWORK OPTIMIZER SEARCH
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining update rules for training neural networks. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective update rule; for each output sequence in the batch: training a respective instance of a child neural network using the update rule defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.