By carrying out advanced experiments on neuronal cultures and large scale simulations, a group of scientists from Bar-Ilan University in Israel claims to have created a new type of ultra-fast artificial intelligence algorithm.
This algorithm is based on the dynamics of the human brain, which, despite computing at a much slower rate than modern computers, is extremely fast and efficient.
Rebuilding the neuroscience AI connection
In an article published today in the journal Scientific Reports, researchers claim to be rebuilding the bridge between neuroscience and advanced artificial intelligence algorithms that, they say, has taken a backseat for almost 70 years.
"The current scientific and technological viewpoint is that neurobiology and machine learning are two distinct disciplines that advanced independently," the study's lead author, Prof. Ido Kanter, of Bar-Ilan University's Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center said in a press release. "The absence of expectedly reciprocal influence is puzzling."
"Biological hardware (learning rules) is designed to deal with asynchronous inputs and refine their relative information," he continued.
Meanwhile, traditional artificial intelligence algorithms are based on synchronous inputs. Due to this, the relative timing of different inputs constituting the same frame is usually ignored.
The following diagram shows the way that a synchronous input (computer) presents all objects simultaneously, whereas an asynchronous input (human brain) presents objects in a timed order.
Ultra-fast learning rates
The new paper demonstrates how ultra-fast learning rates are surprisingly identical for networks that are large as well as small.
So "the disadvantage of the complicated brain's learning scheme is actually an advantage," the researchers say.
The researcher's paper takes on the guise of a call-to-action: by rebuilding the bridge between neurobiology and artificial intelligence - that the researchers claim has been broken - we can gain "insights of fundamental principles of our brain."
The brain has "to be once again at the center of future artificial intelligence," they say.
By learning to mimic the efficiency of the human brain, a new class of ultra-fast advanced artificial intelligence based on brain dynamics could be created.