arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12431cs.LGcs.NE
收藏

柔性相位动力学用于生物可塑性对比学习

Flexible Phase Dynamics for Bio-Plausible Contrastive Learning

Universite de Montreal(蒙特利尔大学);Mila, Quebec AI Institute(米拉魁北克人工智能研究所)

Ezekiel Williams, Colin Bredenberg, Guillaume Lajoie

AI总结:

本研究提出柔性相位动力学,使对比学习在生物和神经形态系统中实现时间局部化,并放宽标准训练要求,通过定理和实验验证其有效性,为相关研究奠定理论基础。

摘要:

许多在神经科学中作为规范模型或作为神经形态芯片学习候选方法的机器学习算法,通过对比一组网络状态与另一组网络状态来进行学习。这些对比学习(CL)算法传统上采用刚性、时间非局部且周期性的学习动力学实现,这可能限制了能够利用CL的物理系统的范围。在本研究中,我们基于近期探索生物或神经形态系统如何实现CL的工作,表明这种学习形式可以变得时间局部化,并且即使在标准训练过程的许多动力学要求被放宽的情况下仍能正常工作。得益于一组通用定理以及跨多个CL模型的数值实验验证,我们的结果为生物和神经形态神经网络中CL方法的研究与发展提供了理论基础。

英文摘要:

Many learning algorithms used as normative models in neuroscience or as candidate approaches for learning on neuromorphic chips learn by contrasting one set of network states with another. These Contrastive Learning (CL) algorithms are traditionally implemented with rigid, temporally non-local, and periodic learning dynamics that could limit the range of physical systems capable of harnessing CL. In this study, we build on recent work exploring how CL might be implemented by biological or neurmorphic systems and show that this form of learning can be made temporally local, and can still function even if many of the dynamical requirements of standard training procedures are relaxed. Thanks to a set of general theorems corroborated by numerical experiments across several CL models, our results provide theoretical foundations for the study and development of CL methods for biological and neuromorphic neural networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑