External Learning & Competitions
I collect the Kaggle problems I studied and describe only the runs and results I can still confirm.
Kaggle · OUTTA Basic
28×28 grayscale sign-language image classification; the historical notebook resized inputs for VGG16
Local rerun: accuracy 1.0000; balanced accuracy 1.0000; macro-F1 1.0000
Read the project noteKaggle · OUTTA Basic
binary text classification with BERT
Local rerun: accuracy 0.9896; balanced accuracy 0.9307; F1 0.8879; precision 0.9115; recall 0.8655; AP 0.9187
Read the project noteKaggle · OUTTA Basic
audio classification from rhythm and spectral features
Local rerun: accuracy 0.8142; balanced accuracy 0.8120; macro-F1 0.8108
Read the project note