Glossary
A procedure in which systems are trained by labeled input-output pairs and tuned until outputs match target labels.
Topic brief
A Jiang Lens evidence brief for this topic, built from source tags, transcript matches, and linked source refs.
supervised learning
A procedure in which systems are trained by labeled input-output pairs and tuned until outputs match target labels.
Showing 7 evidence items
No matching evidence on this topic page.
Key Notes
definition
He frames supervised learning as query-response optimization that can be technically simple (input-to-output fitting) but opaque at high complexity, undermining semantic interpretation of outputs.
Timestamped Evidence
Transcript
"...doesn't exist what exists is going to call supervised supervised machine learning this is the technical term okay right supervised machine learning okay and..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"...the output will be two okay very simple how surprised machine learning works is okay this is fine for simple problems but there's certain..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"trying to figure out what the weighting is and I could try to play play by myself like say one percent two percent five..."
Sources:
Reading
Transcript
YouTube
Data
Transcript
"...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 call..."
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.