US 12,361,305 B2
Neural architecture search for convolutional neural networks
Vijay Vasudevan, Los Altos Hills, CA (US); Barret Zoph, Sunnyvale, CA (US); Jonathon Shlens, San Francisco, CA (US); and Quoc V. Le, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Apr. 20, 2023, as Appl. No. 18/137,398.
Application 18/137,398 is a continuation of application No. 16/674,801, filed on Nov. 5, 2019, granted, now 11,651,259.
Application 16/674,801 is a continuation of application No. 16/040,067, filed on Jul. 19, 2018, granted, now 10,521,729.
Claims priority of provisional application 62/535,806, filed on Jul. 21, 2017.
Prior Publication US 2023/0252327 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/046 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01)
CPC G06N 5/046 (2013.01) [G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/0002 (2013.01); G06T 2207/20084 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A neural network system comprising one or more computers and one or more non-transitory computer storage media encoded with instructions that, when executed by the one or more computers, cause the one or more computers to implement:
a sequence of convolutional cells, the sequence of convolutional cells comprising a plurality of convolutional cells of a first type configured to receive a cell input and to generate a cell output,
wherein each convolutional cell of the first type comprises a sequence of a predetermined number of operation blocks that each receive one or more respective input hidden states and generate a respective output hidden state, wherein one or more operation blocks in the sequence are configured to perform one or more convolution operations on one or more respective input hidden states that the one or more operation blocks receive, and
wherein each of the one or more operation blocks in the sequence of the predetermined number of operations blocks included in the convolutional cell of the first type is configured to:
apply a first operation to a first input hidden state to generate a first output;
apply a second operation to a second input hidden state to generate a second output; and
apply a combining operation to the first and second outputs to generate a respective output hidden state for the operation block,
wherein for each convolutional cell of the first type following the first convolutional cell of the first type in the sequence, at least one of the first input hidden state or the second input hidden state is an output of a previous convolutional cell in the sequence or an output of a previous operation block in the convolutional cell of the first type.