Google releases Tensorflow Lite to bring on-device machine learning

Nov. 20, 2017, 9:06 p.m. By: Pranjal Kumar

Tensor flow Lite

Google has recently released Tensorflow Lite (a software for machine learning developers which can take AI to the next level). Google wants to develop AI system capable of running algorithms on a mobile device (without connecting to the cloud). They believe that it is the basic groundwork for the artificial intelligence of things (AioT) of the future.


Currently, three main software that uses AI is Google Assistant, Apple Siri, and Amazon Alexa. You can also get your own AI based application and you just need to have WIFI and a power source.

But, Tensorflow Lite is the basic step on the path toward making AI-powered devices not just accessible, but disposable. Developers can now preview Tensor flow Lite for Android and iOS. Tensorflow Lite is designed to leverage existing hardware (like the Snapdragon 835 processors used inside latest smartphones) to run algorithms typically impossible for mobile devices without connecting to the cloud.

Google’s Tensorflow Lite will allow developers to run AI models on a smartphone and, upon adding new data, run those algorithms to determine new outcomes. This will basically free developers from needing internet connectivity to test AI application for smartphones.

Some of the basic aims for Tensorflow Lite are (specified by Google) :

  1. Allow developers to get free from the need for internet connectivity.

  2. Enhance the security by not allowing user data to leave form the mobile device.

  3. Widely-available smart appliances create new possibilities for on-device intelligence.

Google’s Tensorflow Lite is paving the way for voice-controlled disposables built on cheap chips and AI-powered appliances that don’t expose your entire network to unethical hackers. These efforts form Google is the main reason why the company dominates in the field of AI and machine learning.