Machine learning uses the speed of modern computers, large datasets, and deep learning algorithms to produce comparable results to those of human experts in various applicable fields, but with different aspects that are far from current knowledge of learning in neuroscience.
In a new study by the group of scientists at Bar-Ilan University has demonstrated a whole new type of ultrafast artificial intelligence algorithms based on advanced experiments on neuronal cultures and large scale simulations.
Through this study, Scientists have rebuilt the scaffold among neuroscience and progressed artificial intelligence calculations that have been left practically futile for right around 70 years.
In addition, the study demonstrates that ultrafast learning rates are surprisingly identical for small and large networks.
The study’s lead author, Prof. Ido Kanter, of Bar-Ilan University’s Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center, said, “The current scientific and technological viewpoint is that neurobiology and machine learning are two distinct disciplines that advanced independently. The absence of expectedly reciprocal influence is puzzling.”
“The number of neurons in a brain is less than the number of bits in a typical disc size of modern personal computers, and the computational speed of the brain is like the second hand on a clock, even slower than the first computer invented over 70 years ago. In addition, the brain’s learning rules are very complicated and remote from the principles of learning steps in current artificial intelligence algorithms.”
“Brain dynamics do not comply with a well-defined clock synchronized for all nerve cells since the biological scheme has to cope with asynchronous inputs, as physical reality develops. “When looking ahead one immediately observes a frame with multiple objects. For instance, while driving one observes cars, pedestrian crossings, and road signs, and can easily identify their temporal ordering and relative positions.”
“Biological hardware (learning rules) 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.”
“Another important finding is that learning can occur without learning steps through self-adaptation according to asynchronous inputs. This type of learning-without-learning occurs in the dendrites, several terminals of each neuron, as was recently experimentally observed. In addition, network dynamics under dendritic learning are governed by weak weights which were previously deemed insignificant.”
Scientists noted, “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. It calls for the reinitiation of the bridge from neurobiology to artificial intelligence.”
The study is published in the journal Scientific Reports.