My project is a quantum machine learning application geared towards chemical and statistical research. For this project I trained a multivariate linear regression system on a quantum computer. This works by using a quantum computer’s unique properties to plot out data points and create a predictive line of best fit for the graph. This allows for accurate predictions of statistical reliance. For my use case, I trained the model to predict the price of a housing unit based on square footage. This training example is a proof of concept for my application. In the future, I would like to enhance this to the point where it could potentially predict molecular properties of compounds larger than beryllium hydride, in order to help further research into chemical simulation. To build this algorithm I used IBM’s Watson quantum computer through their new cloud streaming service.

What inspired you (or your team)?

I have always been interested in the Quantum World. This almost magical field of study where almost anything seems possible. As I started to study Quantum Physics, I noticed that most simulations used to study Quantum Phenomenon were being run using classical systems. This simply does not make sense. As Richard Feynman said “Nature isn’t classical, dammit, and if you want to make a simulation of nature, you’d better make it quantum mechanical, and by golly it’s a wonderful problem, because it doesn’t look so easy.” That’s why I started this project in hopes of making a contribution to the growing effort to create an effective way of simulating nature as she is; absurd.