WASHINGTON: Researchers from Massachusetts Institute of Technology (MIT) have developed a system that could improve the ability of computers to draw commonalities from unstructured data and help humans improve decision-making.

While computers are good at identifying patterns in huge data sets, humans, by contrast, are good at inferring patterns from just a few examples.

The new prototype-based machine learning system bridges these two ways of processing information, so that humans and computers can collaborate to make better decisions, the researchers said.

"In this work, we were looking at whether we could augment a machine-learning technique so that it support people in performing recognition-primed decision-making," said Julie Shah, assistant professor of aeronautics and astronautics at MIT and the study co-author.

In experiments, human participants using the new system were more than 20 percent better at classification tasks than those using a similar system based on existing algorithms.

The MIT researchers made two major modifications to the type of algorithm commonly used in unsupervised learning in which computer simply looks for commonalities in unstructured data.

The first is that the clustering was based not only on data items' shared features, but also on their similarity to some representative example, which the researchers dubbed a "prototype".

The other is rather than simply ranking shared features according to importance, the way a topic-modelling algorithm might, the new algorithm tries to winnow the list of features down to a representative set, which the researchers dubbed a "subspace".

The findings will be presented at Neural Information Processing Society's conference next week in Montreal, Canada.

READ MORE: Tibet Launches General Survey Of Classics Collections and Arvind Kejriwal To Address Students At Columbia University