Home / My courses / UGRD-AI6100-2323T / MIDTERM EXAMINATION / MIDTERM EXAM

Started on Monday, 4 March 2024, 9:47 AM

State Finished
Completed on Monday, 4 March 2024, 10:00 AM
Time taken 13 mins 1 sec
Marks 40.00/40.00
Grade 100.00 out of 100.00

Question 1
Correct

Mark 1.00 out of 1.00

What is the first step in processing a prompt by an LLM?

a. None of the above

b. Generating a response
c. Breaking it down into individual words and phrases
d. Both A and B

Question 2
Correct

Mark 1.00 out of 1.00

What are prompts in the context of AI generative models?

a. Instructions that tell the model what to do.

b. Data used for training and evaluating prompts.
c. Negative words that confuse models.
d. Examples of creative content.

Question 3
Correct

Mark 1.00 out of 1.00

What is the neural network used by DALL-E 2 to generate images?

a. LSTM
b. GAN
c. LLM
d. CLIP


Question 4

Correct

Mark 1.00 out of 1.00

What is the recommended approach for writing a good prompt for 3DFY.ai?

a. Avoiding specific details

b. Using vague language
c. Being specific and using keywords
d. Including negative words

Question 5
Correct

Mark 1.00 out of 1.00

What are the tips for improving prompts?

a. Be clear and concise

b. Use keywords that are relevant to the task
c. Be specific about what you want the app to do
d. Avoid using negative words

Question 6

Correct

Mark 1.00 out of 1.00

How does the generator in 3DFY.ai learn to generate 3D images closer to the prompt description?

a. Through supervised learning

b. Through unsupervised learning
c. Through reinforcement learning
d. Through generative adversarial networks (GANs)

Question 7
Correct

Mark 1.00 out of 1.00

What is the purpose of using examples in prompt engineering?

a. To avoid using keywords.

b. To confuse the model.
c. To provide context for the prompt.
d. To avoid experimentation.


Question 8

Correct

Mark 1.00 out of 1.00

What is the pattern used by an LLM to generate a response?

a. The pattern in the dataset used to train the LLM

b. The pattern in the individual words and phrases of the prompt
c. None of the above
d. Both A and B

Question 9
Correct

Mark 1.00 out of 1.00

What is the use of negative words in prompt engineering?

a. They confuse the model.

b. They are not used in prompt engineering.
c. They help the model understand the task.
d. They are used for positive prompts.

Question 10

Correct

Mark 1.00 out of 1.00

What is the best way to learn how to improve prompts?

a. Both A and B
b. Experiment with different types of prompts
c. Use the same prompt over and over again
d. None of the above

Question 11
Correct

Mark 1.00 out of 1.00

What are LLMs?

a. Both A and B
b. Large Language Models
c. Little Language Models
d. None of the above


Question 12

Correct

Mark 1.00 out of 1.00

What type of machine learning model is a generative adversarial network (GAN)?

a. A model that can only classify images.

b. A model that can only generate text.
c. A model that can only generate images.
d. A model that can generate realistic images.

Question 13
Correct

Mark 1.00 out of 1.00

What is the main responsibility of prompt engineers?

a. To reduce the capabilities of AI generative models.

b. To create prompts that are unclear and ambiguous.
c. To develop new and innovative techniques to improve the performance of AI generative models.
d. To avoid developing new and innovative techniques.

Question 14

Correct

Mark 1.00 out of 1.00

What type of artificial intelligence is used in 3DFY.ai to learn to create realistic outputs?

a. Unsupervised learning
b. Reinforcement learning
c. Supervised learning
d. Generative adversarial networks (GANs)

Question 15
Correct

Mark 1.00 out of 1.00

What is the goal of prompt engineering?

a. To create prompts that confuse the AI generative models.

b. To create prompts that are difficult for the model to understand.
c. To create prompts that are unclear and ambiguous.
d. To create prompts that are clear, concise, and effective.


Question 16

Correct

Mark 1.00 out of 1.00

What is the technique used by DALL-E 2 to ensure that the generated image is realistic and matches the text description?

a. GAN
b. CLIP
c. LLM
d. LSTM

Question 17
Correct

Mark 1.00 out of 1.00

What is the primary technique used by 3DFY.ai to generate 3D models from text descriptions?

a. Supervised learning
b. Generative adversarial networks (GANs)
c. Reinforcement learning
d. Unsupervised learning

Question 18

Correct

Mark 1.00 out of 1.00

What is the future of prompt engineering?

a. It will become less important.

b. It will lead to reduced bias in AI generative models.
c. It will not evolve.
d. It will not be used in new applications.

Question 19
Correct

Mark 1.00 out of 1.00

What is the primary focus of the reference material provided for Prompt Engineering for Text-Based Generative Art?

a. Use of GANs in 3D image generation

b. Application of 3DFY.ai in product design
c. Reinforcement learning techniques
d. Techniques for writing effective prompts


Question 20

Correct

Mark 1.00 out of 1.00

What is the purpose of the diffusion model in DALL-E 2?

a. To generate images instantly from text descriptions.

b. To classify images based on text descriptions.
c. To gradually transform a random image into an image that matches the features.
d. To convert images into text descriptions.

Question 21
Correct

Mark 1.00 out of 1.00

What are prompts?

a. None of the above

b. Patterns used to generate a response
c. Instructions given to an AI generative app
d. Both A and B

Question 22

Correct

Mark 1.00 out of 1.00

What is the main focus of prompt engineering?

a. To avoid developing new and innovative techniques.

b. To create biased output.
c. To reduce the capabilities of AI generative models.
d. To create prompts that are clear, concise, and effective.

Question 23
Correct

Mark 1.00 out of 1.00

What is the context of the prompt?

a. It confuses the app

b. It helps the app to understand what you are asking for
c. None of the above
d. Both A and B


Question 24

Correct

Mark 1.00 out of 1.00

What is the role of experimentation in prompt engineering?

a. To avoid improving the performance of AI generative models.

b. To use the same prompt repeatedly.
c. To avoid trying different prompts.
d. To learn how to improve prompts.

Question 25
Correct

Mark 1.00 out of 1.00

What is the main challenge in prompt engineering?

a. Lack of experimentation.
b. Lack of data for training prompts.
c. Lack of a standard methodology.
d. Lack of AI generative models.

Question 26

Correct

Mark 1.00 out of 1.00

What is DALL-E 2?

a. A large language model developed by OpenAI.

b. A video game.
c. A music streaming service.
d. A social media platform.

Question 27
Correct

Mark 1.00 out of 1.00

What is the importance of writing clear and concise prompts?

a. To confuse the app

b. To get better results from the app
c. Both A and B
d. None of the above


Question 28

Correct

Mark 1.00 out of 1.00

What does the size of the GAN affect in 3DFY.ai?

a. The number of prompts accepted

b. The quality of the 3D images generated
c. The type of GAN used
d. The speed of 3D image generation

Question 29
Correct

Mark 1.00 out of 1.00

How does DALL-E 2 generate images from text descriptions?

a. By using a technique called reinforcement learning.

b. By using a technique called supervised learning.
c. By using a technique called diffusion modeling.
d. By using a technique called unsupervised learning.

Question 30

Correct

Mark 1.00 out of 1.00

What is the function of the gan_optimizer in the 3DFY.ai code snippet?

a. Updating the weights of the networks

b. Training the discriminator network
c. Evaluating the quality of 3D images
d. Generating 3D images

Question 31
Correct

Mark 1.00 out of 1.00

What type of learning technique is used to train the neural network in DALL-E 2?

a. Semi-supervised learning
b. Reinforcement learning
c. Unsupervised learning
d. Supervised learning


Question 32

Correct

Mark 1.00 out of 1.00

What is the purpose of the provided references and supplementary materials in the document?

a. To showcase unrelated content

b. To provide additional resources for further learning
c. To advertise products and services
d. To list the names of the authors

Question 33
Correct

Mark 1.00 out of 1.00

What is the dataset used to train LLMs?

a. None of the above

b. Both A and B
c. Massive datasets of text and code
d. Small datasets of text and code

Question 34

Correct

Mark 1.00 out of 1.00

What is the effect of using negative words in a prompt?

a. None of the above

b. It confuses the app
c. Both A and B
d. It helps the app to understand the prompt better

Question 35
Correct

Mark 1.00 out of 1.00

What is the role of the generator network in the 3DFY.ai code snippet?

a. Training the discriminator network

b. Evaluating the quality of 3D images
c. Providing prompts for 3D image generation
d. Generating 3D images from prompts


Question 36

Correct

Mark 1.00 out of 1.00

What is the purpose of the gan_train_step function in the 3DFY.ai code snippet?

a. Training the discriminator network

b. Generating 3D images
c. Evaluating the quality of 3D images
d. Updating the weights of the networks

Question 37
Correct

Mark 1.00 out of 1.00

What is the potential application of DALL-E 2 mentioned in the document?

a. Creating educational materials

b. Creating music albums
c. Creating weather forecasts
d. Creating cooking recipes

Question 38

Correct

Mark 1.00 out of 1.00

Why are keywords important in prompt engineering?

a. They confuse the model.

b. They are not important in prompt engineering.
c. They help the model understand the task.
d. They are used for negative prompts.

Question 39
Correct

Mark 1.00 out of 1.00

What does the provided code do with the text description and the diffusion model?

a. Converts the text description into audio

b. Generates the image
c. Analyzes the text description
d. Translates the text description into multiple languages


Question 40

Correct

Mark 1.00 out of 1.00

What is the role of the discriminator in the 3DFY.ai model?

a. Evaluating the quality of 3D images

b. Generating 3D images
c. Providing prompts for 3D image generation
d. Training the generator network

◄ PRELIM LAB EXAM

Jump to...

MIDTERM LAB EXAM ►