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.
Deep Learning
A transcript-matched topic anchored by excerpts such as "...hold in an oddly specific patterns or are completely incorrect. A deep learning model might recognize pedestrians only by the crosswalks underneath them and..."
Showing 11 evidence items
No matching evidence on this topic page.
Topic Scope And Freshness
A transcript-matched topic anchored by excerpts such as "...hold in an oddly specific patterns or are completely incorrect. A deep learning model might recognize pedestrians only by the crosswalks underneath them and..."
Key Notes
Timestamped Evidence
Transcript
"...hold in an oddly specific patterns or are completely incorrect. A deep learning model might recognize pedestrians only by the crosswalks underneath them and..."
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
Transcript
"...neural network. Okay? Um the back learning back propagation is called deep learning and this together is called AI. Okay? That's it. Okay? That's..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"...back propagation I don't call it back propagation I call it deep learning you see and I don't call it supervised machine learning I..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"...a pedestrian fatality. Fatility. A fatality. Investigation found that the car's deep learning model simply didn't register Hasburgs as a person. Experts concluded that..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"...I'm going to engage in the process of deep reflection and deep learning, deep reading this summer so that in September, in the fall,..."
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
Reading
Jiang explains the channel from the inside: a teacher leaving Beijing, watching Iran and Israel move toward world war, and trying to turn a student review archive into a new history that can explain...
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.