- [Narrator] We know that model creation … doesn't really happen today on mobile devices, … but that doesn't answer the question … of where should the model run? … Where the model is created, … and the need to access large amounts of data … to create that model in the first place, … really shouldn't be a large deciding factor … with figuring out where the model should run. … When looking at what does matter, … there are several advantages to … running the model server-side. … Server-side machine learning offerings … usually have prebuilt endpoints … to send back information for reinforcement learning. … This makes creating a feedback mechanism … relatively simple for a developer. … Since the model is server-side … and all the evaluation of it takes place on the server, … any reinforcement learning that takes place … to update the model can immediately be used by all clients. … The services also tend to be implemented using rest APIs. … So it really doesn't matter if a client SEK exists or not. …
- Defining machine learning
- Training a machine learning model
- Comparing machine learning frameworks
- Using IBM Watson for mobile machine learning
- Using Azure Machine Learning for speech and image recognition
- Training Core ML models
- Comparing client-side and server-side models
Skill Level Beginner
Machine Learning for iOS Developerswith Brian Advent1h 25m Advanced
1. Introduction to Machine Learning
2. Server Models: IBM Watson
3. Server Models: Azure Machine Learning
4. Client Models: Core ML
5. Understanding the Offerings
Next steps1m 40s
- 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.