Blog

Decoding Decision-making: Embracing Explainable AI for Trust and Transparency

Book Title: Exploring the Frontiers of Artificial Intelligence and Machine Learning Technologies

Editors:  Mr. Agha Urfi Mirza and Dr. Balraj Kumar

ISBN:  978-81-970457-9-0

Chapter: 3

DOI:   https://doi.org/10.59646/efaimltC3/133

Authors:  Dr. B. Sasikala1 and Shubham Sachan2

1Guest Lecturer, Department of Computer Science, Government Arts and Science College for Women, Orathanadu, Tamil Nadu India
2Research Scholar, Department of Industrial Engineering Management, Maulana Azad National Institute of Technology, MANIT, Bhopal India.

Abstract:

In the rapidly evolving landscape of artificial intelligence (AI), understanding the decision-making processes of AI systems is paramount. As AI becomes increasingly integrated into various facets of society, concerns about transparency and trust in these systems have come to the forefront. This paper explores the emergence of Explainable AI (XAI) as a solution to address these concerns, shedding light on the previously opaque decision-making processes of AI. By delving into the concept of AI as a “black box,” this paper highlights the challenges posed by the lack of transparency in AI decision-making, including concerns about biases, unforeseen consequences, and potential misuse. XAI is presented as a powerful tool for unveiling the inner workings of AI systems, offering insights into how algorithms reach specific decisions and thereby fostering accountability, transparency, and trust. The evolution of XAI techniques, from interpretable machine learning to neural network interpretability, is examined, alongside the importance of clear communication, user-friendly interfaces, and accessible explanations in building trust and understanding in AI systems.

References

  1. Jobin, A., Ienca, M. and Vayena, E. (2019) The Global Landscape of AI Ethics Guidelines. Nature Machine Intelligence, 1, 389-399.
  2. European Commission (2024). Policy recommendations for fostering trustworthy AI.
  3. Samek, W., Montavon, G., Lapusch, A., Anders, C., & Müller, K.-R. (2p19). Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. Springer
  4. Tolga Bolukbasi, Kai-Wei Chang, James Y. Zou, Venkatesh Saligrama, Adam T. Kalai (2016). Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In Advances in Neural Information Processing Systems (pp. 4349-4357).
  5. Dr. A. Akila, Dr. R. Parameswari, Dr. P. Sujatha and Ms. R. Padma, (2023). Fundamentals Of Artificial Intelligence And Machine Learning, San International Scientific Publications, ISBN: 978-81-965552-9-0, DOI: https://doi.org/10.59646/faiml/042.
  6. Dr. Sarika T. Deokate, Dr. Vishal Ratansing Patil, Dr. Yogesh Jadhav, Dr. Satpalsing Devising Rajput and Dr. Deepak Dharrao, (2023). Fundamentals Of Artificial Intelligence And Machine Learning, San International Scientific Publications, ISBN: 978-81-965302-9-7, DOI: https://doi.org/10.59646/faiml/036.