Rule induction
Definition
Rule induction is a symbolic machine learning method that derives if-then rules directly …
Interpretability
Polysemanticity
Definition
Polysemanticity is a characteristic observed in deep neural networks, particularly in …
Owain Evans
Definition
Owain Evans is a computer scientist and educator, currently associated with the Center …
Neuro-symbolic AI
Definition
Neuro-symbolic AI integrates sub-symbolic neural learning methods with symbolic …
Mechanistic interpretability
Definition
Mechanistic interpretability focuses on reverse-engineering neural networks to understand …
Explainable artificial intelligence
Definition
As machine learning models become more complex, particularly deep neural networks, their …
ExBERT
Definition
ExBERT provides interpretability for the BERT transformer model by analyzing the …
Decision list
Definition
A decision list is a type of machine learning model that represents knowledge as a …
Class activation mapping
Definition
CAM generates heatmaps overlaid on input images to show which pixels contributed most to …
black-box
Definition
In AI, a black-box model refers to complex systems like deep neural networks where the …
Understanding
Definition
AI understanding goes beyond statistical correlation to interpret the underlying meaning …