Machine learning was introduced 70 years ago. It is based on the operation of our brain. Using the speed of modern computers and large data sets, deep learning algorithms have recently produced results comparable to those of human experts in various fields, but they are not yet using the advantages of the recent develeopents in neuroscience.
Using advanced experiments on neuronal cultures and large scale simulations, a group of scientists at Bar-Ilan University in Israel has demonstrated a new type of ultrafast artifical intelligence algorithms which outperform learning rates achieved to date by state-of-the-art learning algorithms.
The researchers rebuild the bridge between neuroscience and advanced artificial intelligence algorithms that has been left virtually useless for almost 70 years.
Comparing with the Computers, the computational speed of the brain is very slow, even slower than the first computer invented over 70 years ago.
But still the current AI systems are not much effective than the Brain. The reason is, the current AI systems take synchronous input whereas the Brain can take Asynchronous input.
Brain dynamics do not comply with a well-defined clock synchronized for all nerve cells.
For example, while driving one observes cars, pedestrian crossings, and road signs, and can easily identify their temporal ordering and relative position.
i-e The biological system is designed to deal with asynchronous inputs and refine their relative information.
In contrast, traditional artificial intelligence algorithms are based on synchronous inputs, hence the relative timing of different inputs constituting the same frame is typically ignored.
The idea of efficient deep learning algorithms based on the very slow brain’s dynamics offers an opportunity to implement a new class of advanced artificial intelligence based on fast computers. i-e We will be getting a very powerful system by combining strenth of both Brain and Computer.
News Source: Eurekalert
