New algorithm enables complex calculations on PCs

European researchers have unveiled an algorithm that they claim can solve complex problems easily and accurately — even on a personal computer.

In the past, we have seen a constant rate of acceleration in information processing power as predicted by Moore’s Law, but it now looks as if this exponential rate of growth is limited. New developments rely on artificial intelligence and machine learning, but the related processes are largely not well known and understood.

“Many machine learning methods, such as the very popular deep learning, are very successful, but work like a black box, which means that we don’t know exactly what is going on,” said Professor Susanne Gerber, a specialist in bioinformatics at Johannes Gutenberg University Mainz. “We wanted to understand how artificial intelligence works and gain a better understanding of the connections involved.”

Together with Professor Illia Horenko, a computer expert at Università della Svizzera italiana, Prof Gerber has developed a technique for carrying out incredibly complex calculations at low cost and with high reliability. The researchers summarised their concept in a study published in the journal Science Advances.

According to Profs Gerber and Horenko, the process is based on the Lego principle, according to which complex systems are broken down into discrete states or patterns. With only a few patterns or components, ie, three or four dozen, large volumes of data can be analysed and their future behaviour can be predicted.

“This method enables us to carry out tasks on a standard PC that previously would have required a supercomputer,” said Prof Horenko. It all works on an ordinary PC and has an error rate that is said to be 40% better than the computer systems usually used by weather services, whilst also being much cheaper.

“For example, using the SPA algorithm we could make a data-based forecast of surface temperatures in Europe for the day ahead and have a prediction error of only 0.75°C,” said Prof Gerber. SPA, or, scalable probabilistic approximation, is a mathematically based concept that could be useful in various situations that require large volumes of data to be processed automatically.

In addition to weather forecasts, the research has numerous possible applications such as in solving classification problems in bioinformatics, image analysis and medical diagnostics. For example, in the situation where a large number of cells needed to be classified and grouped, “we can then get an understanding of what characteristics were used to sort the cells”, Prof Gerber noted.

Another potential area of application is neuroscience. Automated analysis of EEG signals could form the basis for assessments of cerebral status. It could even be used in breast cancer diagnosis, as mammography images could be analysed to predict the results of a possible biopsy.

“The SPA algorithm can be applied in a number of fields, from the Lorenz model to the molecular dynamics of amino acids in water,” Prof Horenko said. “The process is easier and cheaper and the results are also better compared to those produced by the current state-of-the-art supercomputers.”

Image credit: ©stock.adobe.com/au/metamorworks

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletter and bimonthly magazine.