Download pdf
The emergence and need for explainable AI
- 1 Capitol Technology University
* Author to whom correspondence should be addressed.
Abstract
Artificial Intelligence (AI) systems, particularly deep learning models, have revolutionized numerous sectors with their unprecedented performance capabilities. However, the intricate structures of these models often result in a "black-box" characterization, making their decisions difficult to understand and trust. Explainable AI (XAI) emerges as a solution, aiming to unveil the inner workings of complex AI systems. This paper embarks on a comprehensive exploration of prominent XAI techniques, evaluating their effectiveness, comprehensibility, and robustness across diverse datasets. Our findings highlight that while certain techniques excel in offering transparent explanations, others provide a cohesive understanding across varied models. The study accentuates the importance of crafting AI systems that seamlessly marry performance with interpretability, fostering trust and facilitating broader AI adoption in decision-critical domains.
Keywords
explainable AI, deep learning, interpretability, trust in AI, model transparency
[1]. Russell, S. J., & Norvig, P. (2020). Artificial intelligence: A modern approach. Malaysia; Pearson Education Limited.
[2]. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
[3]. Zhang, Q., Yang, Y., Ma, H., & Yoshihira, K. (2018). Interpreting deep learning models—a survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(6), e1340.
[4]. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., ... & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities, and challenges toward responsible AI. Information Fusion, 58, 82-115.
[5]. Pearl, J. (2018). Theoretical impediments to machine learning with seven sparks from the causal revolution.
[6]. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144).
[7]. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in neural information processing systems (pp. 4765-4774).
[8]. Lakkaraju, H., Bach, S. H., & Leskovec, J. (2016). Interpretable decision sets: A joint framework for description and prediction. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1675-1684).
[9]. Lou, Y., Caruana, R., & Gehrke, J. (2012). Intelligible models for classification and regression. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 150-158).
[10]. Selbst, A. D., & Barocas, S. (2018). The intuitive appeal of explainable machines. Fordham L. Rev., 87, 1085.
[11]. Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1-38.
[12]. Yeh, C. K., Kim, J., Yen, I. E., & Ravikumar, P. (2019). Representer point selection for explaining deep neural networks. In Advances in Neural Information Processing Systems (pp. 9235-9245).
[13]. Chen, J., Li, L., & Gogate, P. (2018). Learning interpretable deep state space models for probabilistic time series forecasting. In Advances in Neural Information Processing Systems (pp. 10810-10820).
[14]. Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images. Tech Report.
[15]. Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011). Learning word vectors for sentiment analysis. In Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies (pp. 142-150).
[16]. Dua, D., & Graff, C. (2017). UCI Machine Learning Repository.
[17]. Ras, G., van Gerven, M., & Haselager, P. (2018). Explanation methods in deep learning: Users, values, concerns and challenges. In Explainable and interpretable models in computer vision and machine learning (pp. 19-36). Springer.
[18]. Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019). Machine learning interpretability: A survey on methods and metrics. Electronics, 8(8), 832.
[19]. Alvarez-Melis, D., & Jaakkola, T. S. (2018). A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (pp. 4124-4133).
[20]. Doshi-Velez, F., & Kim, B. (2020). Considerations for evaluation and generalization in interpretable machine learning. In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (pp. 3-17). Springer.
Cite this article
Chia,H.L.B. (2023). The emergence and need for explainable AI. Advances in Engineering Innovation,3,1-4.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Journal：Advances in Engineering Innovation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).