Translate to multiple languages

Subscribe to my Email updates

https://feedburner.google.com/fb/a/mailverify?uri=helgeScherlundelearning
Enjoy what you've read, make sure you subscribe to my Email Updates

Tuesday, April 11, 2017

Google Makes Your Smartphone Smarter With Federated Learning | Forbes

Photo: Kevin Murnane
"Google is working on a machine learning technique that allows deep learning models that reside on a mobile device to learn directly from the user’s input without having to send the user's data to the cloud." says Kevin Murnane, writes about technology, science and video games.

Deep learning on a smartphone.
Photo: Gerd Rohs Design/Pixabay

The result is immediate improvements in performance for the user, subsequent improvements for all users, and increased privacy. They call it federated learning and it has the potential to be a game changer.

There are two main processes involved in deep learning, training and inference. The network learns during training and uses what it learned to draw inferences from data. Sophisticated deep learning networks are trained on massive data sets that often reside on multiple machines located in data centers. The amount of data needed for training precludes training on mobile devices.

This doesn’t mean that apps can’t benefit from deep learning; they can and do as anyone knows who has used Google Search or Assistant on their smartphone. The way this usually works is that training takes place in the cloud and inference happens on the user's phone. User data is sent from the phone to the cloud where the deep learning model lives. Data from millions of users is used to train the model and an improved version of this shared model is pushed down to users' phones.  The version of the model that lives on the user's phone carries out inference processes.

In a system like this, the model on the user’s device doesn’t get better by learning directly from the user, it improves by learning from all users. In other words, the user's model isn't tuned to how the user uses the app, it's tuned to how everyone uses the app. Federated learning changes this by allowing the user’s model to learn from both the user and everyone else.

Learning on the phone (A). Averaging in the cloud (B). Training the shared model (C).
Photo: Google
Here’s how it works. The user’s model is improved by learning directly from the user’s input using a restricted version of Tensorflow, Google’s machine learning platform. The user benefits immediately because her model has learned to respond to the way she uses her app. The changes made to the user’s model are summarized in a small update that is sent to the shared model in the cloud where it is averaged with updates from other users. The averaged data is used to refine the shared model through further training and the improved model is pushed down and integrated with the model on the user’s cell phone. 
Read more... 

Source: Forbes