wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Oracle AI Foundations Quiz (Questions 1-15)

Total questions: 15

Worksheet time: 8mins

Name
Class
Date
1.

What is the primary difference between supervised and unsupervised learning?

a)

Supervised learning uses labeled data; unsupervised learning does not.

b)

Supervised learning is only for images; unsupervised is only for text.

c)

Unsupervised learning always produces better accuracy.

d)

Supervised learning requires no human input.

2.

Which of the following is a key characteristic of Convolutional Neural Networks (CNNs)?

a)

They use convolutional layers that preserve spatial relationships.

b)

They cannot be used for image tasks.

c)

They only work with sequential data like time series.

d)

They have no trainable parameters.

3.

Which model type is best suited for sequence tasks such as language or time series?

a)

Feedforward neural networks

b)

Sequence models (RNNs, LSTMs, Transformers)

c)

K-means clustering

d)

Decision trees

4.

Generative AI systems are primarily used for which of the following tasks?

a)

Only data cleaning

b)

Creating new content (text, images, code) from learned patterns

c)

Only model explainability

d)

Enforcing data privacy

5.

Which statement best describes a Large Language Model (LLM)?

a)

A) A small model that performs arithmetic faster than humans.

b)

B) A model trained on large corporal of text to generate or understand language.

c)

C) A rule-based chatbot with no learned parameters.

d)

D) A model that cannot be fine-tuned.

6.

Which OCI capability is most relevant for deploying AI models at scale on Oracle Cloud?

a)

OCI Block Storage only

b)

OCI AI Services / OCI Data Science / OCI AI Infrastructure

c)

OCI DNS

d)

OCI Marketplace exclusively

7.

What is ‘vector search’ typically used for in AI applications?

a)

Searching plain text by exact match only

b)

Finding semantically similar items using vector embeddings

c)

Replacing relational databases entirely

d)

Encrypting data for storage

8.

Which of the following is a common metric for classification tasks?

a)

Mean Absolute Error (MAE)

b)

Accuracy, Precision, Recall, F1-score

c)

BLEU score (only for images)

d)

Throughput (network metric)

9.

Prompt engineering for LLMs is primarily about:

a)

Building physical prompts for robots

b)

Crafting input text to steer model outputs toward desired responses

c)

Optimizing GPU memory usage

d)

Training the LLM from scratch

10.

Which step is most important to reduce model bias and ethical risk before production?

a)

Ignore bias — models are objective

b)

Perform dataset audit, bias tests, and apply mitigation strategies

c)

Increase model size only

d)

Only deploy to test users and hope for the best

11.

Which of these is a reason to use transfer learning?

a)

To always avoid using pre-trained models

b)

To fine-tune a model trained on large data for a specific, smaller task

c)

To reduce accuracy on new tasks

d)

To convert unsupervised problems to supervised automatically

12.

A ‘skill check’ or lab in the OCI AI Foundations course typically helps students to:

a)

Replace theoretical study entirely

b)

Gain hands-on experience applying concepts on OCI resources

c)

Avoid using cloud resources

d)

Learn only marketing material

13.

Deep learning models always require more data than simpler machine learning models to reach good performance.

a)

True

b)

False

14.

Generative AI cannot be regulated because it’s impossible to trace outputs.

a)

True

b)

False

15.

Embeddings convert items (text, images) into numerical vectors that capture semantic meaning.

a)

True

b)

False