Kuiz Pengesanan Drift Model

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

1. Apakah perbezaan antara drift data dan drift konsep?
   • Hanyutan data mengubah pengagihan input; drift konsep mengubah hubungan input-ke-output
   • Mereka adalah dua nama untuk perkara yang sama
   • Hanyutan data hanya menjejaskan imej; hanyutan konsep hanya mempengaruhi teks
   • Hanyutan data berlaku dalam latihan; hanyutan konsep berlaku dalam ujian
2. How should a team interpret a PSI value such as 0.30?
   • As a guarantee that model accuracy has fallen
   • As a signal to investigate under the chosen monitoring policy, not a universal proof of harmful drift
   • As an identical threshold for every feature and population
   • As proof that retraining must begin immediately
3. Mengapakah pengesanan drift berasaskan input boleh memberi amaran awal?
   • Kerana input selalu salah dahulu
   • Kerana input adalah fail yang lebih kecil
   • Kerana label kebenaran asas selalunya tiba lebih lewat daripada ramalan
   • Kerana model mengabaikan label sepenuhnya
4. What does a two-sample Kolmogorov-Smirnov test compare?
   • The average accuracy of two classifiers only
   • The class labels predicted by a single model
   • The parameter values of two neural networks
   • The empirical cumulative distribution functions of two samples
5. Senario yang manakah merupakan contoh jelas tentang hanyutan konsep?
   • Perkara yang dianggap oleh pengguna 'spam' berubah dari semasa ke semasa walaupun untuk e-mel yang kelihatan serupa
   • Kamera menghasilkan imej yang lebih terang sedikit
   • Umur pelanggan dalam set data kekal sama
   • Set data disimpan dalam format fail baharu
6. What is a safe first response when an input-drift monitor triggers?
   • Automatically deploy a newly retrained model without evaluation
   • Investigate the data and impact, then decide whether retraining or another action is justified
   • Delete the reference data
   • Assume every shift is harmful concept drift
7. What can TensorFlow Data Validation check in an ML pipeline?
   • The causal effect of a feature
   • Whether every model prediction is correct
   • Data schemas and statistics, including unexpected changes
   • The absolute accuracy of an unlabeled dataset
8. What does the Population Stability Index (PSI) measure in a drift-monitoring setup?
   • The model’s accuracy on labeled examples
   • A causal effect of an input feature
   • A universal pass/fail threshold for all models
   • A numerical summary of how binned feature distributions differ between reference and current data