Affiliation:
1. Department of Computer Science, Hanyang University, Seoul 04763, Republic of Korea
Abstract
Deep learning researchers believe that as deep learning models evolve, they can perform well on many tasks. However, the complex parameters of deep learning models make it difficult for users to understand how deep learning models make predictions. In this paper, we propose the specific-input local interpretable model-agnostic explanations (LIME) model, a novel interpretable artificial intelligence (XAI) method that interprets deep learning models of tabular data. The specific-input process uses feature importance and partial dependency plots (PDPs) to select the “what” and “how”. In our experiments, we first obtain a basic interpretation of the data by simulating user behaviour. Second, we use our approach to understand “which” features deep learning models focus on and how these features affect the model’s predictions. From the experimental results, we find that this approach improves the stability of LIME interpretations, compensates for the problem of LIME only focusing on local interpretations, and achieves a balance between global and local interpretations.
Funder
Institute of Information & Communications Technology Planning & Evaluation
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference21 articles.
1. (2018, June 06). Statista. Revenues from the Artificial Intelligence (AI) Market Worldwide from 2016 to 2025. Available online: https://www.statista.com/statistics/607716/worldwide-artificial-intelligence-market-revenues/.
2. Panettam, K. (2017). Gartner Top 10 Strategic Technology Trends for 2018, Gartner, Inc.. Smarter with Gartner.
3. The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery;Lipton;Queue,2018
4. Doshi-Velez, F., and Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv.
5. A survey of methods for explaining black box models;Guidotti;ACM Comput. Surv. (CSUR),2018
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献