The present disclosure provides "rule visualization". A computer includes a processor and a memory including instructions executable by the processor to train a neural network to input data and output a prediction. A policy may be generated based on the data. Force features may be generated based on the policy. Decision nodes may be trained based on the force features and binary vectors from the trained neural network. A decision tree may be generated based on the decision nodes. A decision is generated by inputting a policy to the decision tree. The decision may be compared to the prediction, and the neural network may be retrained based on a difference between the decision and the prediction.
本公开提供“规则可视化”。一种包括处理器和存储器的计算机,所述存储器包括指令,所述指令可由所述处理器执行以便训练神经网络以输入数据并输出预测。可以基于所述数据生成策略。可以基于所述策略生成力特征。可以基于所述力特征和来自经训练的神经网络的二进制向量来训练决策节点。可以基于所述决策节点生成决策树。通过将策略输入到所述决策树来生成决策。可以将所述决策与所述预测进行比较,并且可以基于所述决策与所述预测之间的差异重新训练所述神经网络。
Rule visualization
规则可视化
2024-09-24
Patent
Electronic Resource
Chinese
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
British Library Conference Proceedings | 2008
|British Library Online Contents | 2004
|NTIS | 1984
|Engineering Index Backfile | 1955
Engineering Index Backfile | 1888
|