From Statistical to Causal Learning
We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality. Some of the hard open problems of machine learning and AI are intrinsically related to ca...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We describe basic ideas underlying research to build and understand
artificially intelligent systems: from symbolic approaches via statistical
learning to interventional models relying on concepts of causality. Some of the
hard open problems of machine learning and AI are intrinsically related to
causality, and progress may require advances in our understanding of how to
model and infer causality from data. |
---|---|
DOI: | 10.48550/arxiv.2204.00607 |