Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning.
Emanuele MarconatoAndrea PasseriniStefano TesoPublished in: CoRR (2023)
Keyphrases
- learning process
- learning systems
- learning scheme
- language acquisition
- main contribution
- learning algorithm
- artificial intelligence
- learning mechanism
- dynamic bayesian networks
- human learning
- inference process
- distributed learning
- cognitive abilities
- imitation learning
- causal independence
- learning frameworks
- machine learning
- causal bayesian networks
- representation scheme
- inductive inference
- human experts
- learning tasks
- prediction accuracy
- online learning
- prior knowledge