论文标题
在树体系结构上学习优于卷积前馈网络
Learning on tree architectures outperforms a convolutional feedforward network
论文作者
论文摘要
先进的深度学习体系结构由数十个完全连接和卷积的隐藏层组成，目前已扩展到数百个，远非其生物学实现。它们令人难以置信的生物学动力学依赖于以非本地方式改变重量，因为使用反向传播技术，输出单元和权重之间的路线数通常很大。在这里，开发并应用于CIFAR-10数据库的离线和在线学习，受到基于实验的树突树适应的启发的三层树体系结构。所提出的体系结构的表现优于5层卷积Lenet的可实现的成功率。此外，所提出的建筑的高度修剪的树向反向传播方法，其中一条路线连接一个输出单元和重量，代表了有效的树突深度学习。
Advanced deep learning architectures consist of tens of fully connected and convolutional hidden layers, currently extended to hundreds, are far from their biological realization. Their implausible biological dynamics relies on changing a weight in a non-local manner, as the number of routes between an output unit and a weight is typically large, using the backpropagation technique. Here, a 3-layer tree architecture inspired by experimental-based dendritic tree adaptations is developed and applied to the offline and online learning of the CIFAR-10 database. The proposed architecture outperforms the achievable success rates of the 5-layer convolutional LeNet. Moreover, the highly pruned tree backpropagation approach of the proposed architecture, where a single route connects an output unit and a weight, represents an efficient dendritic deep learning.
