Data privacy
People are becoming more and more sensitive when it comes to their own data privacy. Collecting data through the cloud is more difficult than it's ever been. This may prevent us from being able to train the machine learning model with data that we've collected from the server side. Client-side machine learning based on TensorFlow.js is a solution to this problem. TensorFlow.js makes it possible for us to train the model without us having to send the training data outside of the client's computer. This means that our users can receive the benefits of such machine learning while keeping their data private. The following diagram shows a scenario where TensorFlow.js is useful:
The general model can be distributed from the central ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access