I said to myself, will what we develop have the same human touch, the same feelings we get when we hold a work made by humans?
I think we need to stop and review what we do for future 😔

However, I accidentally forgot to pass it to the error_function during runner model, so the model continued to train and initially produced good results. Upon closer examination, I found that the class with the largest samples were overrepresented, thus exaggerating the model's results.

I was working on a multi-class classification model with 86 categories, but these categories were sparse sampled. One solution was to use a class_weight in the error_function to ensure fairness.

turns out this matters a lot for ML , hypergraphs capture way more context and generalize better
made some slides if you're curious about the difference and why it matters for learning networks

Welcome, if you want to come to this place, it is fun. Search for it (Holy Karbala), the burial place of the Master of Martyrs, Al-Hussein bin Ali bin Abi Talib.

Iraq\Karbala