인과적 인공지능 기반 데이터 분석 기법의 심층 분석을 통한 인과적 AI 기술의 현황 분석
Deep Analysis of Causal AI-Based Data Analysis Techniques for the Status Evaluation of Casual AI Technology
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
With the advent of deep learning, Artificial Intelligence (AI) technology has experienced rapid advancements, extending its application across various industrial sectors. However, the focus has shifted from the independent use of AI technology to its dispersion and proliferation through the open AI ecosystem. This shift signifies the transition from a phase of research and development to an era where AI technology is becoming widely accessible to the general public. However, as this dispersion continues, there is an increasing demand for the verification of outcomes derived from AI technologies. Causal AI applies the traditional concept of causal inference to AI, allowing not only the analysis of data correlations but also the derivation of the causes of the results, thereby obtaining the optimal output values. Causal AI technology addresses these limitations by applying the theory of causal inference to machine learning and deep learning to derive the basis of the analysis results. This paper analyzes recent cases of causal AI technology and presents the major tasks and directions of causal AI, extracting patterns between data using the correlation between them and presenting the results of the analysis.
Abstract
With the advent of deep learning, Artificial Intelligence (AI) technology has experienced rapid advancements, extending its application across various industrial sectors. However, the focus has shifted from the independent use of AI technology to its dispersion and proliferation through the open AI ecosystem. This shift signifies the transition from a phase of research and development to an era where AI technology is becoming widely accessible to the general public. However, as this dispersion continues, there is an increasing demand for the verification of outcomes derived from AI technologies. Causal AI applies the traditional concept of causal inference to AI, allowing not only the analysis of data correlations but also the derivation of the causes of the results, thereby obtaining the optimal output values. Causal AI technology addresses these limitations by applying the theory of causal inference to machine learning and deep learning to derive the basis of the analysis results. This paper analyzes recent cases of causal AI technology and presents the major tasks and directions of causal AI, extracting patterns between data using the correlation between them and presenting the results of the analysis.
참고문헌 (22)
- 인공지능 기술 및 산업 분야별 적용 사례, "국경완", 정보통신기획평가원, 15~27 (1888)
- "ChatGPT" (2023)[URL]
- "Bard" (2023)[URL]
- L. Freeman, "Test and evaluation for artificial intelligence", Insight, 23, pp.27~30 (2020)
- J. Pearl, "Causal inference, Causality: objectives and assessment", 39~58 (2010)
- 방태모, "인과추론과 예측 방법론의 차이", 인과추론 서머워크샵 (2022)
- T. C. Chalmers, "A method for assessing the quality of a randomized control trial", Controlled clinical trials, 2(1), pp.31~49 (1981)
- Z. Gao, "Batched multi-armed bandits problem", Advances in Neural Information Processing Systems, 32 (2019)
- "Multi-armed bandit" (2023)[URL]
- S. Triantafillou, "Score based vs constraint based causal learning in the presence of confounders", Causation: Foundation to Application, pp.59~67 (2016)
- S. M. Lundberg, "A unified approach to interpreting model predictions", Advances in neural information processing systems, 30, pp.4768~4777 (2017)
- D. Janzing, "Feature relevance quantification in explainable AI: A causal problem", International Conference on artificial intelligence and statistics, pp.2907~2916 (2019)
- J. Pearl, "Cambridge University Press", ~ (2000)
- D. Dash, "Sequences of Mechanisms for Causal Reasoning in Artificial Intelligence", Twenty-Third International Joint Conference on Artificial Intelligence, pp.839~845 (2013)
- A. Sangroya, "Guided-LIME: Structured Sampling based Hybrid Approach towards Explaining Blackbox Machine Learning Models", CIKM 2020Workshops (2020)
- R. Guo, "Learning Individual Causal Effects from Networked Observational Data", 13th International Conference on Web Search and Data Mining, pp.232~240 (2020)
- P. E.D. Love, "Explainable artificial intelligence (XAI): Precepts, models, and opportunities for research in construction", Advanced Engineering Informatics, 57 (2023)
- T. Miller, "Explanation in artificial intelligence:Insights from the social sciences", Artificial Intelligence, 267, pp.1~38 (2019)
- L. Cheng, "Evaluation methods and measures for causal learning algorithms", IEEE Transactions on Artificial Intelligence, 3(6), pp.924~943 (2022)
- Z. Zeng, "Intrusion detection framework based on causal reasoning for DDoS", Journal of Information Security and Applications (2022)
- R. Chen, "Ontology-driven learning of bayesian network for causal inference and quality assurance in additive manufacturing", IEEE Robotics and Automation Letters, 6(3), pp.6032~6038 (2021)
- J. Berrevoets, "Causal deep learning", Computer Science, Machine Learning (2023)