A team of artificial intelligence researchers from Northwestern University have built a robot on CogSketch model that will mimic the understanding level of common human beings. This computational model of analogy is based on the structure mapping theory of Northwestern psychology professor Dedre Gentner and the same artificial intelligence platform was previously developed in Forbus’ Laboratory.
According to Ken Forbus this model has the ability to understand the world as adult Americans do with an accuracy of 75 percentages. He further added that the things those are difficult for humans to understand are also difficult to recognise by these robots; best proof that it is mimicking human cognition.
However; it can solve complex visual problems citing as one of the hallmarks of human intelligence. The same model was earlier developed in Forbus’ Laboratory, which had the ability to understand complex sketches and to respond with immediate quality feedback. This model too has been designed with the computational model analogy of Prof Dedre through the help of his structure mapping theory.
Developers are optimistic of bridging the gap between human intelligence and computer through this technology. The visual reasoning solving ability of these models is tested on a nonverbal standardised test that measures abstract reasoning.
The tests are carried out through a visual matrix between CogSketch models and humans. Both were given a task of completing the missing part of a visual matrix with best possible structure those have been provided as options. The result showed that this artificial genius outsmarted humans. This is now leading to a new dimension in artificial intelligence development.
According to Andrew Lovett, a former Northwestern postdoctoral researcher, the models are showing ‘fluid intelligence’-an ability to see, think and answer reasonably. The success of CogSketch models to understand sophisticated relationships shows that there is some big development waiting for higher order cognition, said Lovett.