The brain inspires a new type of artificial intelligence


Machine learning is based on evidence of the dynamics of learning in the brain, introduced 70 years ago. Deep learning algorithms have recently produced using the speed of modern computers and large Dataset comparable to those of human experts in various applicable fields, but with different characteristics. A group of a group of scientists has demonstrated a new type of Ultrafast Artificial Intelligence algorithms—based on the very slow brain dynamics using advanced experiments, which outperform learning rates achieved to date by state-of-the-art learning algorithms. The learning rules of Brain are very complicated and remote from the principles of learning steps in current artificial intelligence algorithms. Since the biological scheme has to cope with asynchronous inputs Brain dynamics do not comply with a well-defined clock synchronized for all nerve cells as physical reality develops. Biological hardware learning rules are designed to deal with asynchronous inputs and refine their relative information, in contrast, traditional artificial intelligence algorithms are based on synchronous inputs. The Ultrafast learning rates are identical for small and large networks according to the new study. The learning can also occur without learning steps through self-adaptation according to asynchronous inputs.