Metric Evaluation

Metric Evaluation

University

10 Qs

quiz-placeholder

Similar activities

Chapter 8: Developing Business IT Solutions

Chapter 8: Developing Business IT Solutions

University

10 Qs

Mengenal Fiber Optik

Mengenal Fiber Optik

2nd Grade - University

15 Qs

Exploring Computer Network Models

Exploring Computer Network Models

10th Grade - University

13 Qs

Analytics_Modeling_W1

Analytics_Modeling_W1

University

15 Qs

Soal Logical Data Warehouse Design

Soal Logical Data Warehouse Design

University

12 Qs

Reinforcement Learning Quiz

Reinforcement Learning Quiz

12th Grade - University

15 Qs

HCI GOMS quiz

HCI GOMS quiz

University

15 Qs

komputasi awan

komputasi awan

University

15 Qs

Metric Evaluation

Metric Evaluation

Assessment

Quiz

Information Technology (IT)

University

Medium

Created by

Anna Baita

Used 3+ times

FREE Resource

AI

Enhance your content in a minute

Add similar questions
Adjust reading levels
Convert to real-world scenario
Translate activity
More...

10 questions

Show all answers

1.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Seorang peneliti membandingkan dua model object detection. Model A: mAP tinggi tapi FPS rendah. Model B: mAP lebih rendah tapi FPS tinggi. Jika model digunakan di mobil otonom, mana lebih baik?

Model A

Model B

Sama saja

Tidak bisa dipakai

2.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Seorang data enginer ingin membangun model prediksi penyakit langka. Namun dataset penyakit langka tersebut jumlahnya kecil, sehingga evaluasi tidak boleh bergantung threshold. Metrik yang tepat menilai performa model tersebut adalah:

Accuracy

ROC-AUC

Recall

RMSE

3.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Model YOLO mendeteksi objek dengan IoU rendah. Apa artinya

Bounding box tidak pas menutupi objek

Model overfitting

Recall rendah

Akurasi tinggi

4.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

BLEU score digunakan untuk:

Evaluasi terjemahan otomatis

Evaluasi regresi

Evaluasi object detection

Evaluasi akurasi

5.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Gmail menggunakan model klasifikasi spam. User lebih marah jika email normal masuk folder spam. Metrik penting yang harus bernilai tinggi adalah:

Recall

Precision

Accuracy

F1-score

6.

FILL IN THE BLANK QUESTION

1 min • 1 pt

Jika Model prediksi gaji: memiliki data aktual = [50, 60, 70] dalam juta rupiah, dan hasil prediksinya adalah= [55, 65, 65]. Hitung MAE.

7.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Sebuah rumah sakit melatih model deteksi kanker payudara. Model A: Precision = 95%, Recall = 60%. Model B: Precision = 70%, Recall = 90%. Dokter ingin jangan sampai pasien sakit lolos terdeteksi sehat. Model terbaik adalah:

Model A

Model B

Sama saja

Tidak bisa dibandingkan

Create a free account and access millions of resources

Create resources

Host any resource

Get auto-graded reports

Google

Continue with Google

Email

Continue with Email

Classlink

Continue with Classlink

Clever

Continue with Clever

or continue with

Microsoft

Microsoft

Apple

Apple

Others

Others

By signing up, you agree to our Terms of Service & Privacy Policy

Already have an account?