Review the services and steps involved in hosting custom machine learning models on virtual machines on GCP.
- [Instructor] Now that we've seen…our first custom ML model, let's look at the steps that…are typically involved to host a production level model.…And there are a lot of them.…So you can see on the left side here, often times,…the model is developed in a notebook, as I showed.…A step that I skipped, but we saw in an earlier movie…is an addition to the analysis that the ML library…or other libraries provide.…It's typical that a customer will use something…like BigQuery to simply do sequel queries against the data…to look for outliers in problematic data.…
In addition to that, production customers…often use Cloud Dataflow, as I showed much earlier…in this course to do transformations based on,…for example, dictionary look ups,…so something like normalizing the names of a city.…So if you had Los Angeles, LA, so on and so forth,…just having it be transformed into a standardized value…in a large dataset is something typically handled…in a service like Dataflow.…Now Dataflow, of course, you might remember,…is the graphical user interface to Dataprep,…
- 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.