Deep Learning · Level 2 of 5
Representation Learning
Learning useful data features as part of the training process.
The system discovers an encoding instead of relying only on manually chosen descriptors.
Example
An audio model learns features useful for recognizing speech.
Listen to the definition and example
Audio transcript
Representation Learning. Learning useful data features as part of the training process. The system discovers an encoding instead of relying only on manually chosen descriptors. For example: An audio model learns features useful for recognizing speech.
Explore this concept
Why it matters
This helps explain why a neural model learns well, becomes unstable, or fails to generalize.
Related concepts
Quick recall question
Try answering before looking back at the definition.