Journal
IEEE ACCESS
Volume 9, Issue -, Pages 18670-18681Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3051171
Keywords
Heating systems; Predictive models; Deep learning; Neurons; Data models; Visualization; Licenses; Layer-wise relevance propagation (LRP); explainable artificial intelligence (XAI); model-specific explanation; visual explanation; heatmap generation
Categories
Funding
- Korea Electric Power Corporation [R18XA05]
Ask authors/readers for more resources
Deep learning has shown excellent performance in various AI fields, but the black-box problem complicates the interpretation of models and predictions. With the introduction of explainable AI, various methods have been proposed to visually explain model predictions. In this study, a selective layer-wise relevance propagation method is introduced, which produces a clearer heatmap by combining relevance-based and gradient-based methods.
Deep learning has recently been applied to various artificial intelligence (AI) fields and has demonstrated excellent performance. However, several models based on deep learning encounter black-box problem that complicates the interpretation of the models and understand their predictions. This makes it difficult to apply deep learning to real problems, especially in critical systems such as those in the defense, aerospace, and security domains. To overcome this issue, the concept of explainable AI was introduced. Various approaches have been proposed to visually explain model predictions for image and text classification. A common approach for visual explanation includes layer-wise relevance propagation (LRP), which produces a heatmap where each pixel value represents a contribution to the prediction of the model. Advanced versions of LRP have been proposed, but these methods have some limitations. In this study, we propose selective layer-wise relevance propagation, which produces a clearer heatmap than the existing methods by combining relevance-based methods and gradient-based methods. The experimental results are presented qualitatively and quantitatively to evaluate the proposed method and verify its effectiveness.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available