Google Launches TensorFlow Lite for Mobile Machine Learning
App developers will soon have a specialized version of TensorFlow to work on Android devices, maximizing available resources. It will be called TensorFlow Lite and it is a part of the open source project maintained by Google.
TensorFlow is an open source software library for diverse applications of machine learning, used for computation, data analysis and verification, and of course the underlying design and training of machine learning algorithms. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google’s Machine Intelligence research department for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well. TensorFlow is one of the more complex projects maintained by Google, and it has been used by all sorts of developers and researches for fields ranging from economics to healthcare. You can learn more about it by visiting its website.
TensorFlow Lite, a streamlined version of TensorFlow for mobile, was announced by Dave Burke, vice president of engineering for Android. Mr. Burke said: “TensorFlow Lite will leverage a new neural network API to tap into silicate specific accelerators, and over time we expect to see DSPs (Digital Signal Processors) specifically designed for neural network inference and training.” He also added: “We think these new capabilities will help power the next generation of on-device speech processing, visual search, augmented reality, and more.” TensorFlow Lite comes at a time where silicon manufacturers like Qualcomm have begun adding on-chip machine learning capabilities to their products, and as OEMs have increasingly been adopting varying degrees of “AI” into their ROMs.
Dave Burke finally stated that TensorFlow Lite is a part of Google’s plan to keep devices smarter. We can interpret it as the company’s attempt to bring Artificial Intelligence into apps, and further spread the benefits of machine learning across the Android ecosystem.
Source: Venture Beat