论文标题
前馈神经架构空间的本地最佳网络分析
A Local Optima Network Analysis of the Feedforward Neural Architecture Space
论文作者
论文摘要
这项研究调查了局部最佳网络（LON）分析（候选解决方案的健身景观的衍生物）的使用，以表征和可视化神经体系结构空间。通过在数据集选择中评估训练有素的模型性能，可以完全列举馈电神经网络体系结构的搜索空间，最多三层，最多10个神经元。提取的摩尔虽然在数据集各个数据集的同时都表现出简单的全球结构，但在所有情况下都具有单个全球漏斗。这些结果提出了早期的迹象表明，兰斯可能会提供一个可行的范式来分析和优化神经体系结构。
This study investigates the use of local optima network (LON) analysis, a derivative of the fitness landscape of candidate solutions, to characterise and visualise the neural architecture space. The search space of feedforward neural network architectures with up to three layers, each with up to 10 neurons, is fully enumerated by evaluating trained model performance on a selection of data sets. Extracted LONs, while heterogeneous across data sets, all exhibit simple global structures, with single global funnels in all cases but one. These results yield early indication that LONs may provide a viable paradigm by which to analyse and optimise neural architectures.
