Open zhujl3 opened 3 years ago
Wow, thanks for identifying this! Definitely a very important bug. Are you able to re-run the fixed code on any of the existing benchmarks (Gehler Shi or Cheng)? Updating the error metric structs in the *Hyperparams.m
files under /projects/
with this bug fix would be very helpful for everyone using this code.
When I reviewed the code in internal/TrainModel.m, line 283 ~ 288, the original codes are as below:
Since model.W{1} changed before model.b{1} it will lead a computational mistake to model.b{1}.And this mistake may weaken the model performance. So I simply change the code order as below:
And after this change, I got a significant improvement in my experiment.^.^