![Fig. 1: The NSPS searches The NSDP, through backpropagation g to update α and β. The decision policy generated by NSDP is further used for planning and control. Semi-transparent operators shows the candidates for parent operations used in the search from NSPS [700].](https://www.researchgate.net/publication/360513136/figure/fig1/AS:1154388701777921@1652239122859/The-NSPS-searches-The-NSDP-through-backpropagation-g-to-update-a-and-b-The-decision_Q320.jpg)
![Fig. 5: League training as proposed in [745].](https://www.researchgate.net/publication/360513136/figure/fig5/AS:1154388705968143@1652239123760/League-training-as-proposed-in-745_Q320.jpg)
May 2022
·
764 Reads
·
1 Citation
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.