Any Quote by Geoffrey Hinton
“A deep-learning system doesn't have any explanatory power.”
About This Quote
Source Conference: NIPS 2017 keynote, Geoffrey Hinton, 2017
Deep‑learning models can predict accurately but often cannot explain why they make a prediction.
In simple terms: Models predict without clear explanations.
Key Takeaway
Seek interpretability methods.
Themes
AI
explainability
deep learning
Mood
critical
analytical
Type
technical
philosophical
When to use this quote
- diagnosing medical images
- credit scoring
- legal evidence
- scientific discovery
Key Concepts
black‑box
causality
model transparency
Questions to Reflect On
- How can we balance accuracy and explainability?
- What tools help reveal model reasoning?
A Different Perspective
Interpretability may reduce performance or be costly.
