公开(公告)号：US20240104394A1

公开(公告)日：2024-03-28

申请号：US18012387

申请日：2022-03-11

Applicant: Google LLC

Inventor： Amy Skerry-Ryan ,  Quentin Lascombes de Laroussilhe ,  Ronald Rong Yang ,  Carla Marie Riggi ,  Chansoo Lee ,  Jordan Arthur Grimstad ,  Christopher Mark Lamb ,  Joseph Michael Moran ,  Nihesh Anderson Klutto Milleth ,  Noah Weston Hadfield-Menell ,  Volodymyr Shtenovych ,  Ziqi Huang ,  Sagi Perel ,  Michael David Gerard ,  Mehadi Seid Hassen

IPC: G06N3/10 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06N3/10 ,  G06N3/045 ,  G06N3/08

Abstract: Provided are computing systems, methods, and platforms that automatically produce production-ready machine learning models and deployment pipelines from minimal input information such as a raw training dataset. In particular, one example computing system can import a training dataset associated with a user. The computing system can execute an origination machine learning pipeline to perform a model architecture search that selects and trains a machine learning model for the training dataset. Execution of the origination machine learning pipeline can also result in generation of a deployment machine learning pipeline configured to enable deployment of the machine learning model (e.g., running the machine learning model to produce inferences and/or optionally other tasks such as re-training and/or re-tuning the model). The computing system can export the machine learning model and the deployment machine learning pipeline for deployment of the machine learning model with the deployment machine learning pipeline

公开(公告)号：US20240378484A1

公开(公告)日：2024-11-14

申请号：US18288442

申请日：2022-09-13

Applicant: Google LLC

Inventor： Walter Bogorad ,  Ronald Rong Yang ,  Alexander Troesch ,  Bavin Amenya Ondieki ,  Yousef Khaled Nassar

IPC: G06N20/00

Abstract: Aspects of the disclosure are directed to retraining an ensemble machine learning model. The ensemble model can include a base model and an overlay model. The base model can be trained on an older dataset, validated, and manually verified. The overlay model can be trained on a newer dataset and automatically validated. A combination of base model predictions and overlay model predictions, with bias towards the base model predictions, can form ensemble model predictions. A model weight for optimizing the ensemble model can determine the bias, as well as indicate that the overlay model contributes too much or too little to the ensemble model.