US 12,267,089 B2
Systems and methods for improved machine-learned compression
Eirikur Thor Agustsson, Zürich (CH); and Lucas Marvin Theis, Berlin (DE)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 18/008,045
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Jun. 3, 2021, PCT No. PCT/US2021/035672
§ 371(c)(1), (2) Date Dec. 2, 2022,
PCT Pub. No. WO2021/247840, PCT Pub. Date Dec. 9, 2021.
Claims priority of provisional application 63/034,172, filed on Jun. 3, 2020.
Prior Publication US 2023/0299788 A1, Sep. 21, 2023
Int. Cl. H03M 7/30 (2006.01); G06N 3/0455 (2023.01); G06N 3/084 (2023.01)
CPC H03M 7/3059 (2013.01) [G06N 3/0455 (2023.01); G06N 3/084 (2013.01)] 42 Claims
OG exemplary drawing
 
1. A computer-implemented method for compressing computer-readable data having improved efficiency, the method comprising:
obtaining, by a computing system comprising one or more computing devices, input data associated with the computing system; and
encoding, by the computing system, the input data and added noise from a noisy channel to produce encoded data based at least in part on a machine-learned encoder model, wherein encoding the input data and added noise comprises additively combining the added noise and the input data to obtain noisy input data and rounding the noisy input data by a soft rounding function, the soft rounding function having a sharpness, to produce the encoded data;
wherein the machine-learned encoder model is trained on training data, wherein the training data is encoded with the added noise from the noisy channel.