Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Log-Loss (Gubitak logaritma / Križna entropija)× | F1-mjera× | |
|---|---|---|
| Područje | Evaluacija modela | Evaluacija modela |
| Obitelj | MCDM | MCDM |
| Godina nastanka≠ | 1990s | 1979 |
| Tvorac≠ | Information theory and machine learning literature | C. J. van Rijsbergen |
| Vrsta≠ | Loss function | Evaluation metric |
| Temeljni izvor≠ | Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. link ↗ | van Rijsbergen, C. J. (1979). Information Retrieval (2nd ed.). Butterworth-Heinemann. link ↗ |
| Drugi nazivi | Cross-Entropy Loss, Logloss | F-measure, Harmonic Mean |
| Srodne≠ | 3 | 5 |
| Sažetak≠ | Log-loss measures the difference between predicted probabilities and actual labels, penalizing confident wrong predictions more than uncertain ones. It is a standard loss function in machine learning optimization and evaluates probabilistic classifier calibration. | The F1-score is the harmonic mean of precision and recall, providing a single metric that balances both concerns. It was introduced by van Rijsbergen in information retrieval and has become a standard metric for evaluating classification models where both precision and recall are important. |
| ScholarGateSkup podataka ↗ |
|
|