2023-05-26 18:52:08 +01:00
|
|
|
# Activation Maximisation
|
|
|
|
- Synthesise an ideal image for a class
|
|
|
|
- Maximise 1-hot output
|
|
|
|
- Maximise [[Activation Functions#SoftMax|SoftMax]]
|
|
|
|
|
|
|
|
![[am.png]]
|
|
|
|
- **Use trained network**
|
|
|
|
- Don't update weights
|
2023-05-27 00:50:46 +01:00
|
|
|
- [[Architectures|Feedforward]] noise
|
|
|
|
- [[Back-Propagation|Back-propagate]] [[Deep Learning#Loss Function|loss]]
|
2023-05-26 18:52:08 +01:00
|
|
|
- Don't update weights
|
|
|
|
- Update image
|
|
|
|
|
|
|
|
![[am-process.png]]
|
|
|
|
## Regulariser
|
|
|
|
- Fit to natural image statistics
|
|
|
|
- Prone to high frequency noise
|
|
|
|
- Minimise
|
|
|
|
- Total variation
|
2023-05-27 00:50:46 +01:00
|
|
|
- $x^*$ is the best solution to minimise [[Deep Learning#Loss Function|loss]]
|