Artificial intelligence has a feel for laboratory science

PhD students Chris Lovell and Gareth Jones received the Carl Smith Award on 8 October for best student paper at the 13th international conference on Discovery Science.

The artificial intelligence, developed by Chris Lovell, is claimed to mimic the techniques used by human scientists.

The ‘artificial experimenter’ software looks at the data available, builds hypotheses and then chooses the experiments to perform, all without human interaction.

‘Experimentation is expensive. Scientists always want to learn as much as they can from the smallest number of experiments possible. The new techniques we have developed try to address this problem,’ said Dr Klaus-Peter Zauner of the Science and Engineering of Natural Systems Group at ECS, who supervised this research as part of a Microsoft European Fellowship.

As well as learning from small numbers of experiments, the software is designed to question whether the data obtained is correct.

‘Biological experimentation can be error prone,’ Dr Zauner added. ‘Measurements taken may not always be representative of what actually happens. Our system tries to detect erroneous data, so it can ignore it.’