Department of Physics, Bar-Ilan University, Ramat-Gan, 52900, Israel.
Gonda Interdisciplinary Brain Research Center and the Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, 52900, Israel.
Sci Rep. 2020 Apr 23;10(1):6923. doi: 10.1038/s41598-020-63755-5.
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.
几十年来，研究人员一直试图模仿大脑的功能，在神经科学和人工智能之间架起桥梁；然而，实验神经科学并没有直接推动机器学习（ML）领域的发展。在这里，我们使用神经元培养物证明了增加训练频率可以加速神经元适应过程。该机制在人工神经网络上得以实现，在人工神经网络中，对于一致的连续学习步骤，局部学习步长会增加，并在手写数字 MNIST 的简单数据集上进行了测试。基于我们用几个手写示例进行的在线学习结果，受大脑启发的算法的成功率大大超过了常用的 ML 算法。我们推测，这种从缓慢的大脑功能到 ML 的新兴桥梁将促进在有限示例下的超快速决策，这在人类活动、机器人控制和网络优化的许多方面都是现实情况。
