Deep Jointly-Informed Neural Networks
Deep Jointly-Informed Neural Networks
复制标题
DOI：
--
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
K. Humbird;J. Peterson;R. McClarren
中科院分区：
文献类型：
--
作者：
K. Humbird;J. Peterson;R. McClarren
在这项工作中，提出了一种新颖的自动化过程，用于确定适当的深度神经网络架构和基于决策树的权重初始化。该方法将根据数据训练的决策树集合映射到初始化的神经网络集合，网络的结构由树的结构决定。这些模型被称为“深度联合通知神经网络”，展示了对各种数据集的高预测性能。此外，该算法很容易融入贝叶斯框架，从而产生准确且可扩展的模型，为预测提供量化的不确定性。
In this work a novel, automated process for determining an appropriate deep neural network architecture and weight initialization based on decision trees is presented. The method maps a collection of decision trees trained on the data into a collection of initialized neural networks, with the structure of the network determined by the structure of the tree. These models, referred to as "deep jointly-informed neural networks", demonstrate high predictive performance for a variety of datasets. Furthermore, the algorithm is readily cast into a Bayesian framework, resulting in accurate and scalable models that provide quantified uncertainties on predictions.