“we allow small jumps that the optimizer can recover from…” — Practical AI at 22:07
“we allow small jumps that the optimizer can recover from and adjust the remaining weights for rather than doing it all at once. And the all at once piece is where we get into post-training in one shot, where we're not going to try and retrain the model at all. We're going to take a small calibration data set. And…”
0:00
38:28