Kuiz Fungsi Kehilangan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

1. For a prediction task, what does its selected loss quantify against the training target?
   • A specified prediction-error objective
   • Only runtime speed
   • Only the number of network layers
   • Every application benefit automatically
2. Fungsi kehilangan yang manakah paling biasa digunakan untuk tugas pengelasan?
   • Min ralat kuasa dua
   • Min ralat mutlak
   • Kehilangan entropi silang
   • Jarak engsel sahaja
3. Berbanding dengan min ralat kuasa dua, mengapa anda mungkin memilih min ralat mutlak?
   • Ia mengasingkan kesilapan untuk menghukum mereka lebih banyak
   • Ia lebih teguh kepada outlier kerana ia tidak mengadu ralat
   • Ia tidak boleh digunakan untuk regresi
   • Ia mengabaikan label sebenar
4. Why does gradient-based training need a usable loss derivative or suitable substitute?
   • So a loss number can be printed
   • So all learning methods become identical
   • So the dataset no longer needs targets
   • So backpropagation and optimization can obtain an update signal
5. How does one-hot class cross-entropy change as probability assigned to the target class becomes very small?
   • Its loss must become zero
   • It rewards the prediction increasingly
   • Its loss becomes large
   • It becomes identical to accuracy
6. Mengapakah ketepatan biasanya tidak digunakan secara langsung sebagai kehilangan latihan?
   • Ia tidak boleh dibezakan, jadi ia tidak memberikan kecerunan yang berguna
   • Ia terlalu mudah untuk dikira
   • Ia hanya berfungsi untuk regresi
   • Ia sentiasa sama dengan kerugian pula
7. For illustrative regression residuals one and three, what are mean squared error and mean absolute error?
   • MSE is two and MAE is five
   • Both are four
   • MSE is ten and MAE is four
   • MSE is five and MAE is two
8. Using a base-two logarithm, what one-hot cross-entropy loss corresponds to target-class probability one-quarter?
   • One-quarter bit
   • Two bits
   • Four bits
   • Zero bits