Suite of machine learning products developed by Google that enables people to train machine learning models.
suiteSuite of Machine Learning products developed by Google that enables developers with limited machine learning expertisepeople to train machine learning models.
Google Cloud AutoML is a suite of Machine Learning products that enables developers with limited machine learning expertise to train models. On Jan 17 2018, Google announced AutoML Vision, a new service that helps developers — including those with no machine learning (ML) expertise — build custom image recognition models.
AutoML features easily training of custom vision models, state-of-the-art performance and a simple graphical user interface that allows users to create custom machine learning model in only a few minutes.
It is also integrated with human labeling, by providing a team of in-house human labelers that will review images custom instructions and classify them accordingly while keeping them private. Users can leverage state of the art AutoML and transfer learning technology to produce high quality machine learning models.
At its core, Cloud AutoML is fully integrated with other Google Cloud services, providing customers with a consistent method of access across the entire Google Cloud service line.
Barret Zoph, Vijay Vasudevan, Jonathon Shlens and Quoc Le, Research Scientists, Google Brain Team
AutoML for large scale image classification and object detection
Quoc Le & Barret Zoph, Research Scientists, Google Brain team
Using Machine Learning to Explore Neural Network Architecture
An approach developed by Google by which a controller neural net proposes a 'child' model architecture that can be trained to perform a certain task. The feedback is used to train the controller for future model architecture proposals.
suite of Machine Learning products that enables developers with limited machine learning expertise to train machine learning models.