Kutathmini miundo ya ML inamaanisha kupima jinsi inavyofanya kazi vizuri — kwa kutumia metrics inayofaa (usahihi, precision, recall, nk) kwenye data ya mtihani ambayo muundo haujauona. Tathmini sahihi ni muhimu sana kwa kujua kama muundo hufanya kazi na kuwa na uhakika.
Kutathmini kwenye data isiyojulikana
→ evaluate on a TEST set the model did NOT train on → measures GENERALIZATION (real performance)
→ training accuracy alone is misleading (a model can memorize training data)
→ train/validation/test split; cross-validation → reliable performance estimates
