We, your people and descendants, have not preserved all that our ancestors entrusted to us, yet we strive to reclaim what we can.

We have turned you into a legend, so that we may endure 😓🥺.

#life #AcademicSky #Science #SciComm

Land of writing, poetry, literature, law, and justice. Truly, you are the lost essence of Iraq; the wounded lion that has not yet risen again.

#life #AcademicSky #Science #SciComm

Even though the sun is stationary, the earth's movement causes it to shift, resulting in sunrise and sunset.

and proving it is evidence of that. Also that, the researcher must adhere/take on to all the rules he initially established and not compromise on them, as they represent the foundations of his scientific research.
#AI #MachineLearning #DeepLearning #Research

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.