Skip to main content

Google launches machine learning framework for training quantum models

(Image credit: Image source: Shutterstock/PHOTOCREO Michal Bednarek)

Earlier this week, Google announced a new open-source library for the rapid prototyping of quantum machine learning (ML) models.

Together with the University of Waterloo, NASA's Quantum AI Lab and car manufacturer Volkswagen, Google has released TensorFlow Quantum (TFQ), which provides the tools necessary to bring quantum computing and machine learning together.

While machine learning has a broad range of use cases - such as image processing for cancer detection or forecasting earthquake aftershocks - its scope is limited by the capabilities of the computing device.

But with progress in the quantum computing space, combining the two could have “a profound impact on the world’s biggest problems,” Google believes.

The company expects the new framework to lead to breakthroughs in the areas of medicine, materials, sensing, and communications.

As Google explains, TFQ integrates TensorFlow with open-source network for Noisy Intermediate Scale Quantum computers, Cirq, which allows the framework to build and implement both discriminative and generative quantum-classical models.

According to a VentureBeat report, it provides quantum computing primitives compatible with existing TensorFlow APIs, along with high-performance quantum circuit simulators.

“Today, TensorFlow Quantum is primarily geared towards executing quantum circuits on classical quantum circuit simulators. In the future, TFQ will be able to execute quantum circuits on actual quantum processors that are supported by Cirq, including Google’s own processor Sycamore,” said Google.