Dendritic Computing: Branching Deeper into Machine Learning
Dendritic Computing: Branching Deeper into Machine Learning
复制标题
DOI：
10.1016/j.neuroscience.2021.10.001
复制
发表时间：
2022-04-21
期刊：
影响因子：
3.3
通讯作者：
Wu, Xundong
中科院分区：
文献类型：
--
作者：
Acharya, Jyotibdha;Basu, Arindam;Wu, Xundong
在本文中，我们讨论了生物和人工神经元中树突提供的非线性计算能力。我们首先简要介绍有关树突非线性类型、各自的可塑性规则及其对通过计算模型评估的生物学习的影响的生物学证据。四个主要的计算意义被确定为提高表达能力、更有效地利用资源、利用内部学习信号以及实现持续学习。然后，我们讨论如何使用树突计算来解决现实世界的分类问题，并在机器学习中使用的众所周知的数据集上报告性能。这些作品根据可塑性的三种主要方法进行分类——结构可塑性、重量可塑性或突触延迟可塑性。最后，我们展示了深度学习和树突计算概念之间融合的最新趋势，并强调了一些未来的研究方向。本文是题为：SI：树突对生物和人工计算的贡献的特刊的一部分。 (c) 2022 国际广播组织。由爱思唯尔有限公司出版。保留所有权利。
this paper, we discuss the nonlinear computational power provided by dendrites in biological and artificial neurons. We start by briefly presenting biological evidence about the type of dendritic nonlinearities, respective plasticity rules and their effect on biological learning as assessed by computational models. Four major computational implications are identified as improved expressivity, more efficient use of resources, utilizing internal learning signals, and enabling continual learning. We then discuss examples of how dendritic computations have been used to solve real-world classification problems with performance reported on well known data sets used in machine learning. The works are categorized according to the three primary methods of plasticity used-structural plasticity, weight plasticity, or plasticity of synaptic delays. Finally, we show the recent trend of confluence between concepts of deep learning and dendritic computations and highlight some future research directions.This article is part of a Special Issue entitled: SI: Dendritic contributions to biological and artificial computations. (c) 2022 IBRO. Published by Elsevier Ltd. All rights reserved.