Unknown

Dataset Information

0

Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms.


ABSTRACT: 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.

SUBMITTER: Sardi S 

PROVIDER: S-EPMC7181840 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

altmetric image

Publications

Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms.

Sardi Shira S   Vardi Roni R   Meir Yuval Y   Tugendhaft Yael Y   Hodassman Shiri S   Goldental Amir A   Kanter Ido I  

Scientific reports 20200423 1


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  ...[more]

Similar Datasets

| S-EPMC6688986 | biostudies-literature
| S-EPMC4610387 | biostudies-literature
| S-EPMC9245212 | biostudies-literature
| S-EPMC2773246 | biostudies-literature
| S-EPMC9727201 | biostudies-literature
| S-EPMC6281287 | biostudies-literature
| S-EPMC4914443 | biostudies-literature
| S-EPMC7027398 | biostudies-literature
| S-EPMC10997790 | biostudies-literature
| S-EPMC9839320 | biostudies-literature