.png){kind=icon}
Return
Causal representation learning through higher-level information extraction
.png){kind=icon}
PRE
AI
DOI：10.1145/3696412.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Representation learning
probabilistic programs
object perception
Journal
IF:
28
Papers:
2.5K
Citations:
3.5W
Organization
Cited Papers
BIM-EL localization: The key to understanding anoikis resistance in inflammatory breast cancer cells
OAAI
OAAIShareSaveATG4A promotes tumor metastasis by inducing the epithelial-mesenchymal transition and stem-like properties in gastric cells.png)
Oncotarget
OAAI
OncotargetIF0
OAAIShareSaveShareSaveShareSaveShareSave
View more