Uploaded byManojkumar Parmar
Explainable AI (XAI)
The lightning talk on Explainable AI (XAI) presented by Manojkumar Parmar highlights the importance of understanding AI decisions and the implications of acknowledging the reasoning behind these decisions. Key challenges to adopting trustworthy AI include the opacity of machine learning models and the need for transparency, reliability, and rationality in their outputs. The document references various studies and examples to illustrate the need for explainable AI in real-world applications.
More Related Content
Similar to Explainable AI (XAI)
Explainable AI (XAI)
- 1. EXPLAINABLE AI (XAI) MANOJKUMAR PARMAR ROBERTBOSCH ENGINEERING AND BUSINESS SOLUTIONS PRIVATE LIMITED, INDIA LIGHTNING TALK AT ICACCI’18 ON 21ST SEPTEMBER 2019
- 2. SIMPLE QUESTION BUTFAR REACHING IMPLICATION AI : It’s a cat or not? Key Question: “Why it’s a cat?”
- 3. FROM RESEARCH Brown, T.B., Mané, D., Roy, A., Abadi, M., & Gilmer, J. (2017). Adversarial patch. arXiv preprint arXiv:1712.09665. Kurakin, A., Goodfellow, I., & Bengio, S. (2016). Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533.
- 4. REAL WORLD EXAMPLES:MY EXPERIENCES
- 5. QUESTIONS WE CARE Whydid you do that? Why not something else? When do you succeed? When do you fail? When can I trust you? How do I correct an error?
- 6. CHALLENGES TO ADOPTION •ML/AI Models are Blackbox Models • ML Models are Opaque, Non Intuitive and Difficult for people to understand • Key Issue: Trustworthiness, reliability, rationality, and transparency of Models • Decisions of Machine or action thereby have far reaching impact on Individual, society or Government Understanding Trust Transparency Interaction
- 7.
- 8.
- 9.
- 10.
- 11. REFERENCES • Ribeiro, M.T., Singh, S., & Guestrin, C. (2016, August). 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). ACM. • Fox, M., Long, D., & Magazzeni, D. Explainable Planning. In IJCAI-17 Workshop on Explainable AI (XAI) • Gunning, D. (2017). Explainable artificial intelligence (xai). Defense Advanced Research Projects Agency (DARPA), nd Web. • Miller, T., Howe, P., & Sonenberg, L. (2017). Explainable AI: Beware of inmates running the asylum. In IJCAI-17 Workshop on Explainable AI (XAI)
- 12. XAI: PATH TOWARDSFUTURE OF AI THANK YOU!