Collaborating with the University of Waterloo, Alphabet’s X and carmaker Volkswagen, Google is building an open-source library for quantum machine-learning applications. TensorFlow Quantum (TFQ), the library, is for the rapid prototyping of quantum ML models. With this library, quantum computing and machine learning research communities can together control and model natural or artificial quantum systems  

According to experts, classical ML models that can learn a model of a system and predict the system’s behaviour, have evolved in recent years and can tackle challenging scientific issues, like image processing for cancer detection. This model can also do things like forecast earthquake aftershocks, predict extreme weather conditions or detect new exoplanets. With the current development in the expansion of quantum computing, the development of new quantum ML models could have a heavy impact on the world’s biggest problems, leading to breakthroughs in the areas of medicine, materials, sensing, and communications. Till now, there were no research tools to discover useful quantum ML models which could process quantum data and execute on quantum computers.

 TFQ blends Cirq with TensorFlow and offers high-level ideas for the design and implementation of quantum-classical models. This presents quantum computing primitives compatible with existing TensorFlow APIs, along with high-performance quantum circuit simulators.

“We hope this framework provides the necessary tools for the quantum computing and machine learning research communities to explore models of both natural and artificial quantum systems, and ultimately discover new quantum algorithms which could potentially yield a quantum advantage,” a report posted by Alan Ho, Product Lead and Masoud Mohseni, Technical Lead, Google Research states.