Acquiring a substantial number of data points for training accurate machine learning (ML) models is a big challenge in scientific fields where data collection is resource-intensive. Here, we propose a novel approach for constructing a minimal yet highly informative database for training ML models in complex multi-dimensional parameter spaces. To achieve this, we mimic the underlying relation between the output and input parameters using Gaussian process regression (GPR). Using a set of known data, GPR provides predictive means and standard deviation for the unknown data. Given the predicted standard deviation by GPR, we select data points using Bayesian optimization to obtain an efficient database for training ML models. We compare the performance of ML models trained on databases obtained through this method, with databases obtained using traditional approaches. Our results demonstrate that the ML models trained on the database obtained using Bayesian optimization approach consistently outperform the other two databases, achieving high accuracy with a significantly smaller number of data points. Our work contributes to the resource-efficient collection of data in high-dimensional complex parameter spaces, to achieve high precision machine learning predictions.

As UBDS continues to flourish, we are looking to bring some further expertise to our Data Services practice. You will be able to transform business needs into technical solutions & deliver high quality data solutions to not only meet but surpass our clients expectations. At UBDS we pride ourselves on our ability to not only meet but surpass client expectations and we want to do the same with those who choose to make UBDS a part of their career. In return for making UBDS your working "home", you will receive: UBDS is the go-to digital transformation partner to the public and private sectors. Organisations turn to us for deep knowledge, specialist skills, years of on-the-job experience and our can-do and get-it done culture.

A tax on robots is one of those ideas that sounds attractive, and when it's put forward by someone with the credibility of Bill Gates, as it was in a recent interview with Quartz magazine, you can guarantee it will generate a lot of interest. If he, of all people, says taxing robots is a good idea, then surely it is worth considering? At first pass, the idea feels like common sense. After all, if robots replace workers but don't generate tax revenue, it means not only that the funds available for government services are substantially diminished, but that inequality – already at record levels in developed nations – is likely to increase. Wages that would have been earned by human workers, now displaced by robots, will go straight to profits, increasing the wealth gap between those who own the robots and the growing pool of unemployed workers.