Shrinking Machine Learning Models for Offline Use : Alexa Blogs

Last week, the Alexa Auto team announced the release of its new Alexa Auto Software Development Kit (SDK), enabling developers to bring Alexa functionality to in-vehicle infotainment systems. The initial release of the SDK assumes that automotive systems will have access to the cloud, where the machine-learning models that power Alexa currently reside. But in the future, we would like Alexa-enabled vehicles -- and other mobile devices -- to have recourse to some core functions even when they're offline. That will mean drastically reducing the size of the underlying machine-learning models, so they can fit in local memory. At the same time, third-party developers have created more than 45,000 Alexa skills, which expand on Alexa's native capabilities, and that number is increasing daily. Even in the cloud, third-party skills are loaded into memory only when explicitly invoked by a customer request.