论文标题
参数有效的树突树神经元优于感知
Parameter efficient dendritic-tree neurons outperform perceptrons
论文作者
论文摘要
生物神经元比人工感知龙更强大，部分原因是复杂的树突状输入计算。启发是为了使感知龙具有生物学启发的功能，我们探索了添加和调谐输入分支因子以及输入辍学的效果。这允许发现和基准测试参数有效的非线性输入体系结构。此外，我们提出了一个pytorch模块，以替换现有体系结构中的多层感知层。我们对MNIST分类的最初实验证明了与现有的感知体架构相比，树突神经元的准确性和概括提高。
Biological neurons are more powerful than artificial perceptrons, in part due to complex dendritic input computations. Inspired to empower the perceptron with biologically inspired features, we explore the effect of adding and tuning input branching factors along with input dropout. This allows for parameter efficient non-linear input architectures to be discovered and benchmarked. Furthermore, we present a PyTorch module to replace multi-layer perceptron layers in existing architectures. Our initial experiments on MNIST classification demonstrate the accuracy and generalization improvement of dendritic neurons compared to existing perceptron architectures.
