论文标题
因果贝叶斯神经网络的零售公司绩效的损失收敛
Loss convergence in a causal Bayesian neural network of retail firm performance
论文作者
论文摘要
我们通过在零售购买，零售商店运营和企业绩效[1]上发表的结构方程模型（SEM）扩展了经验结果[1]。当通过使用翻转层的扰动权重提供变异推理时，神经网络收敛显示可随着最弱的SEM路径的去除而改善，而VADAM Optimizer在输出中的扰动权重的结果不确定。
We extend the empirical results from the structural equation model (SEM) published in the paper Assortment Planning for Retail Buying, Retail Store Operations, and Firm Performance [1] by implementing the directed acyclic graph as a causal Bayesian neural network. Neural network convergence is shown to improve with the removal of the node with the weakest SEM path when variational inference is provided by perturbing weights with Flipout layers, while results from perturbing weights at the output with the Vadam optimizer are inconclusive.
