Causal AI is an artificial intelligence system that can explain cause and effect. Causal AI technology is used by organisations to help explain decision making and the causes for a decision.[1][2]

Systems based on causal AI, by identifying the underlying web of causality for a behaviour or event, provide insights that solely predictive AI models might fail to extract from historical data. An analysis of causality may be used to supplement human decisions in situations where understanding the causes behind an outcome is necessary, such as quantifying the impact of different interventions, policy decisions or performing scenario planning.[3][4]

The concept of causal AI and the limits of machine learning were raised by Judea Pearl, the Turing Award-winning computer scientist and philosopher, in The Book of Why: The New Science of Cause and Effect. Pearl asserted: “Machines' lack of understanding of causal relations is perhaps the biggest roadblock to giving them human-level intelligence.”[5][6]

Columbia University has established a Causal AI Lab under Director Elias Bareinboim. Professor Bareinboim’s research focuses on causal and counterfactual inference and their applications to data-driven fields in the health and social sciences as well as artificial intelligence and machine learning.[7] Technological research and consulting firm Gartner for the first time included causal AI in its 2022 Hype Cycle report, citing it as one of five critical technologies in accelerated AI automation.[8][9]

Causal AI GitHub Projects

Causal AI has gained significant traction in recent years, leading to the development of several open-source GitHub projects that aim to provide tools and frameworks for causal inference and analysis. These projects include:

  • CausalML: An extensive Python library developed by Uber for uplift modeling and causal inference using machine learning algorithms. Source
  • DoWhy: A Python library designed for causal inference, supporting explicit modeling and testing of causal assumptions. In a collaboration between Microsoft and Amazon, DoWhy has since evolved into PyWhy, with an independent open-source governance model.[10] Source
  • Salesforce CausalAI Library: A scalable Python framework for causal analysis of time series and tabular data, offering benchmarking modules for comparing different causal discovery algorithms. Source

In addition to these projects, the CEILS methodology (Counterfactual Explanations as Interventions in Latent Space),[11] provides a framework for generating counterfactual explanations that capture the underlying causal relationships in data and provide feasible recommendations for achieving a desired outcome.[12]

These projects represent a growing ecosystem of Causal AI tools and resources, fostering collaboration and innovation in the field. As Causal AI continues to evolve, these open-source contributions will play a crucial role in advancing its capabilities and applications.

References

  1. ↑ Blogger, SwissCognitive Guest (18 January 2022). "Causal AI". SwissCognitive, World-Leading AI Network. Retrieved 11 October 2022.
  2. ↑ Sgaier, Sema K; Huang, Vincent; Grace, Charles (2020). "The Case for Causal AI". Stanford Social Innovation Review. 18 (3): 50–55. ISSN 1542-7099. ProQuest 2406979616.
  3. ↑ Shekhar, Gaurav (26 May 2022). "Causal AI — Enabling Data Driven Decisions". Medium. Retrieved 11 October 2022.
  4. ↑ "How to Understand the World of Causality | causaLens". causalens.com. 28 February 2023. Retrieved 7 October 2023.
  5. ↑ Pearl, Judea (2019). The book of why : the new science of cause and effect. Dana Mackenzie. [London], UK. ISBN 978-0-14-198241-0. OCLC 1047822662.{{cite book}}: CS1 maint: location missing publisher (link)
  6. ↑ Hartnett, Kevin (15 May 2018). "To Build Truly Intelligent Machines, Teach Them Cause and Effect". Quanta Magazine. Retrieved 11 October 2022.
  7. ↑ "What AI still can't do". MIT Technology Review. Retrieved 18 October 2022.
  8. ↑ "What is New in the 2022 Gartner Hype Cycle for Emerging Technologies". Gartner. Retrieved 11 October 2022.
  9. ↑ Sharma, Shubham (10 August 2022). "Gartner picks emerging technologies that can drive differentiation for enterprises". VentureBeat. Retrieved 11 October 2022.
  10. ↑ "DoWhy Evolves to PyWhy | Geminos Software". www.geminos.ai. Retrieved 7 December 2023.
  11. ↑ Crupi, Riccardo; Castelnovo, Alessandro; Regoli, Daniele; San Miguel Gonzalez, Beatriz (2022). "Counterfactual explanations as interventions in latent space". Data Mining and Knowledge Discovery: 1–37.
  12. ↑ FLE-ISP (8 March 2023), CEILS, retrieved 12 December 2023
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.