2 Apr
2022
2 Apr
'22
3:26 p.m.
Daydreaming about that a little. With the pretrained model there are a bunch of logits and other data for each moment of the recording. If the model uncovered the simple nature of the generated recording .. then the same patterns of logits would appear at different moments in the recording. Doing that simple backsolving of a deep model would simply train the model to produce constant output, though. It's could be way more complex than needed. ....