EUVIMEDDescubrir EUVIMED
Open access · CC BY 4.0

Causal representation learning through higher-level information extraction

Francisco Silva, Hélder P. Oliveira, Tania Pereira

ACM Computing Surveys · 2025-02-28 · 57 (2) · 1-37

DOI: 10.1145/3696412 ↗

At a glance

Journal article in ACM Computing Surveys, published online on 2024-11-07. Written by Francisco Silva and 2 co-authors. Cited 5 times so far (Crossref); 285 references. The full text is freely available (open access, CC BY 4.0).

ResumenDatos bibliográficosCiteRelated studies

Abstract (original language)

The large gap between the generalization level of state-of-the-art machine learning and human learning systems calls for the development of artificial intelligence (AI) models that are truly inspired by human cognition. In tasks related to image analysis, searching for pixel-level regularities has reached a power of information extraction still far from what humans capture with image-based observations. This leads to poor generalization when even small shifts occur at the level of the observations. We explore a perspective on this problem that is directed to learning the generative process with causality-related foundations, using models capable of combining symbolic manipulation, probabilistic reasoning, and pattern recognition abilities. We briefly review and explore connections of research from machine learning, cognitive science, and related fields of human behavior to support our perspective for the direction to more robust and human-like artificial learning systems.

Cite

APA

Silva, F., Oliveira, H. P., & Pereira, T. (2025). Causal representation learning through higher-level information extraction. ACM Computing Surveys, 57(2), 1-37. https://doi.org/10.1145/3696412

Vancouver

Silva F, Oliveira HP, Pereira T. Causal representation learning through higher-level information extraction. ACM Computing Surveys. 2025;57(2):1-37. doi:10.1145/3696412

BibTeX
@article{Silva2025,
  author = {Silva, Francisco and Oliveira, Hélder P. and Pereira, Tania},
  title = {Causal representation learning through higher-level information extraction},
  journal = {ACM Computing Surveys},
  year = {2025},
  volume = {57},
  number = {2},
  pages = {1--37},
  doi = {10.1145/3696412}
}
Start for free →