Physicist for the first time have shown that machine learning can reconstruct a quantum system. It can be done based on experimental measurements, and is a method which will allow scientists to probe systems of particles exponentially faster than conventional Brute Force techniques. The complex systems which required thousands of years for reconstruction with conventional methods can now be analysed completely and thoroughly in just a matter of hours. This research is expected to benefit the development of quantum computers and open growth avenues for other applications of quantum mechanics. The scientists have shown that machine intelligence can capture the essence of a quantum system in a compact way.
What got these researchers to use ideas in quantum physics, is the computer program which was used for playing Chinese board game Go in 2016. Machine learning was used by the computer program in order to outplay the Chinese board game Go. Similar to Schrodinger’s cat which can be either dead or alive, systems of particles in existent different configurations each with a particular probability of occurring, and each particle such as electron, can even have an upward or a downward spin.
In quantum mechanics, the entire complexity of a system cannot be determined in a single experiment, rather same measurements are conducted over and over again. However, this method works only for simple systems containing only a few particles, and it would get a lot complicated with more number of particles. Because, as the number of particles increases, even a system with five electrons each electron can either spin up or spin down, 32 configurations possibilities are there. Similarly a system of 100 electrons will have over 1 million trillion trillion possible configurations. This complicates matters and conventional methods can therefore be not feasible to use for complex quantum systems.