当前位置: X-MOL 学术Neural Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multibranch Formal Neuron: An Internally Nonlinear Learning Unit
Neural Computation ( IF 2.9 ) Pub Date : 2021-09-16 , DOI: 10.1162/neco_a_01428
Marifi Güler 1
Affiliation  

The transformation of synaptic input into action potential in nerve cells is strongly influenced by the morphology of the dendritic arbor as well as the synaptic efficacy map. The multiplicity of dendritic branches strikingly enables a single cell to act as a highly nonlinear processing element. Studies have also found functional synaptic clustering whereby synapses that encode a common sensory feature are spatially clustered together on the branches. Motivated by these findings, here we introduce a multibranch formal model of the neuron that can integrate synaptic inputs nonlinearly through collective action of its dendritic branches and yields synaptic clustering. An analysis in support of its use as a computational building block is offered. Also offered is an accompanying gradient descent–based learning algorithm. The model unit spans a wide spectrum of nonlinearities, including the parity problem, and can outperform the multilayer perceptron in generalizing to unseen data. The occurrence of synaptic clustering boosts the generalization efficiency of the unit, which may also be the answer for the puzzling ubiquity of synaptic clustering in the real neurons. Our theoretical analysis is backed up by simulations. The study could pave the way to new artificial neural networks.



中文翻译:

多分支形式神经元:内部非线性学习单元

突触输入向神经细胞动作电位的转化受树突乔木的形态以及突触功效图的强烈影响。树枝状分支的多样性惊人地使单个细胞能够充当高度非线性的处理元件。研究还发现了功能性突触聚类,其中编码共同感觉特征的突触在空间上聚集在树枝上。受这些发现的启发,我们在这里引入了神经元的多分支形式模型,该模型可以通过其树突分支的集体作用非线性地整合突触输入并产生突触聚类。提供了支持将其用作计算构建块的分析。还提供了一个伴随的基于梯度下降的学习算法。该模型单元涵盖了广泛的非线性,包括奇偶校验问题,并且在泛化到看不见的数据方面可以胜过多层感知器。突触聚类的出现提高了单元的泛化效率,这也可能是对突触聚类在真实神经元中普遍存在的困惑的答案。我们的理论分析得到了模拟的支持。这项研究可以为新的人工神经网络铺平道路。

更新日期:2021-09-17
down
wechat
bug