Review an on-device IoT custom ML application that also includes use of GCP services for continuous integration and deployment of the custom machine learning model.
- [Instructor] For our final reference architecture,…we're looking at, of course, the most complex use case,…but one that I am starting to see.…What's really interesting about this…is the continuous deployment and continuous…integration aspect of model building.…An additional aspect that's interesting…about this architecture is that it reflects…the relatively new capability of…running Machine Learning Models on devices.…So let's work through the sections.…Starting on the left, this model…use case is for image rendering…and we're using a third party service,…the Zync Renderer, to kick off the workflow.…
The generated images are then stored in Cloud Storage.…In the next step, we're working with Machine Learning.…So the first portion, we're doing training…using the new images because we're…going to be doing classification,…and we're using a custom machine learning model…that's hosted on Cloud Machine Learning.…The model output or the labels are stored in Cloud Storage.…In the next step, we have packaging.…We have a Training Watcher,…
- Hosting options: Serverless, containers, and virtual machines
- Enabling the GCP ML AIs
- Preparing data with Cloud Dataflow and Dataprep
- Modeling predictions for images, video, text to speech, and cloud translation
- Machine learning with AutoML
- Advanced machine learning and deep learning
- Machine learning architectures
Skill Level Intermediate
1. Machine Learning on Google Cloud Platform
2. Machine Learning API Services
3. Machine Learning with AutoML
Understand AutoML Vision4m 57s
4. Advanced Machine Learning
5. Machine Learning Architectures
Next steps1m 30s
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.