TY - JOUR
T1 - Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms
AU - Sardi, Shira
AU - Vardi, Roni
AU - Meir, Yuval
AU - Tugendhaft, Yael
AU - Hodassman, Shiri
AU - Goldental, Amir
AU - Kanter, Ido
N1 - Publisher Copyright:
© 2020, The Author(s).
PY - 2020/4/23
Y1 - 2020/4/23
N2 - Attempting to imitate the brain’s functionalities, researchers have bridged between neuroscience and artificial intelligence for decades; however, experimental neuroscience has not directly advanced the field of machine learning (ML). Here, using neuronal cultures, we demonstrate that increased training frequency accelerates the neuronal adaptation processes. This mechanism was implemented on artificial neural networks, where a local learning step-size increases for coherent consecutive learning steps, and tested on a simple dataset of handwritten digits, MNIST. Based on our on-line learning results with a few handwriting examples, success rates for brain-inspired algorithms substantially outperform the commonly used ML algorithms. We speculate this emerging bridge from slow brain function to ML will promote ultrafast decision making under limited examples, which is the reality in many aspects of human activity, robotic control, and network optimization.
AB - Attempting to imitate the brain’s functionalities, researchers have bridged between neuroscience and artificial intelligence for decades; however, experimental neuroscience has not directly advanced the field of machine learning (ML). Here, using neuronal cultures, we demonstrate that increased training frequency accelerates the neuronal adaptation processes. This mechanism was implemented on artificial neural networks, where a local learning step-size increases for coherent consecutive learning steps, and tested on a simple dataset of handwritten digits, MNIST. Based on our on-line learning results with a few handwriting examples, success rates for brain-inspired algorithms substantially outperform the commonly used ML algorithms. We speculate this emerging bridge from slow brain function to ML will promote ultrafast decision making under limited examples, which is the reality in many aspects of human activity, robotic control, and network optimization.
UR - http://www.scopus.com/inward/record.url?scp=85083865143&partnerID=8YFLogxK
U2 - 10.1038/s41598-020-63755-5
DO - 10.1038/s41598-020-63755-5
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 32327697
AN - SCOPUS:85083865143
SN - 2045-2322
VL - 10
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 6923
ER -