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.

翻译：先进的深度学习架构包含数十个全连接和卷积隐藏层，目前已扩展至数百层，但其远未实现生物学的真实结构。其非生物合理的动力学依赖非局部的权重调整方式——由于输出单元与权重之间通常存在大量路径，反向传播技术被广泛采用。本文受实验性树突树适应机制启发，提出了一种3层树架构，并将其应用于CIFAR-10数据集的离线与在线学习。所提架构的性能优于5层卷积LeNet的可达成功率。此外，该架构中高度剪枝的树反向传播方法（即输出单元与权重之间仅存在单一路径）代表了高效的树突深度学习。