diagnosis
He describes the black-box nature of deep networks as making model behavior difficult to explain and vulnerable to spurious correlations that fail outside narrow training conditions.
Topic brief
A Jiang Lens evidence brief for this topic, built from source tags, transcript matches, and linked source refs.
Explainability
He describes the black-box nature of deep networks as making model behavior difficult to explain and vulnerable to spurious correlations that fail outside narrow training conditions.
Showing 5 evidence items
No matching evidence on this topic page.
Key Notes
Timestamped Evidence
Transcript
"Neural networks have shown, for example, that they can be unreliable and unpredictable. As statistical pattern matches, they sometimes hold in an oddly specific..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"They cannot explain exactly how they're learning, or how the model will behave, especially in strange edge case scenarios, because the patterns that the..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"The idea of the black box is that weighted system, the neural network. Humans don't actually know what's going on in there, because it's..."
Sources:
Reading
Transcript
YouTube
Data
Relevant Lectures And Readings
Reading
The lecture starts by warning against overconfident certainty, then rewires from literary method to a hard model of AI: today’s systems are pattern-fitters optimized for compliance, so power becomes control over what counts as...
Sources:
Reading
Transcript
YouTube
Data
Related Topics
How To Use And Cite This Page
This topic page is a discovery surface. For generated synthesis, cite the human-readable source reading or lens page. For Jiang-spoken claims, cite the transcript segment, source ref, and YouTube timestamp. Raw text and Markdown mirrors are fallback surfaces for tools that cannot read this HTML page.