In a new study, a team of scientists explains how a new approach significantly improves the ability
We can make AI learn much better if we train them in the way our brains perceive information.
Maximilian Riesenhuber, PhD, Professor of Neurobiology, Georgetown University Medical Center
People can learn new things quickly and wellvisual concepts based on limited data—sometimes just one example is enough. Even three to four month old babies can easily learn to recognize zebras and differentiate them from cats, horses and giraffes. But computers usually need to "see" many examples of the same object to know what it is, Riesenhuber explains.
Therefore it was necessary to developsoftware to determine relationships between entire visual categories, rather than attempting a more standard approach to object identification using only low-level and intermediate information such as shape and color.
The team found that artificial neural networks, which represent objects in terms of previously studied concepts, learn new visual concepts much faster.
The fact is that the architecture of the brain that lies inbased on the study of human visual concepts, based on neural networks involved in object recognition. It is believed that the anterior temporal lobe of the brain contains "abstract" representations that go beyond form. These complex neural hierarchies for visual recognition allow people to learn new tasks and, most importantly, use previously acquired knowledge.
Despite advances in the field of artificialintelligence, the human visual system is still the gold standard in terms of its ability to generalize from multiple examples: it can reliably deal with variations in an image and clearly analyzes what is happening around it.
Read more
Abortion and science: what will happen to the children who will give birth
Check out the most beautiful pictures of Hubble. What has the telescope seen in 30 years?
Named a plant that is not afraid of climate change. It feeds a billion people