Russian scientists have created a neural network that has its own "visual organs" and looks at objects in a similar way as humans do, an article published in the Neural Networks journal said.
"We present an oscillatory neural network model that can account for reaction times in visual search experiments. The model consists of a central oscillator that represents the central executive of the attention system and a number of peripheral oscillators that represent objects in the display," said the researchers from the Institute of Mathematical Problems of Biology at the Russian Academy of Sciences with regard to their invention.
Over the past decade, hundreds of programmers and dozens of large IT companies have created countless machine vision systems that can recognize and classify different objects.
However, despite the tremendous progress in this field, scientists still do not know how we manage to automatically classify and recognize objects that we have never seen before.