imalexsk
No user record in our sample, but imalexsk has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
No user record in our sample, but imalexsk has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
the loss value he mentions for the KAN is ~1/5 (0.00011) of the NN loss (0.006). Could be a massive difference in an actual task with larger/complex datasets.