AI

3/1/24, 10:36 AM MIDTERM LAB EXAM: Attempt review
Home / My courses / UGRD-AI6100-2323T / MIDTERM EXAMINATION / MIDTERM LAB EXAM
Started on Friday, 1 March 2024, 10:25 AM

State Finished
Completed on Friday, 1 March 2024, 10:30 AM
Time taken 4 mins 55 secs
Marks 40.00/40.00
Grade 100.00 out of 100.00
Question 1
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 generate realistic images.

b. A model that can only classify images.
c. A model that can only generate text.
d. A model that can only generate images.
Question 2
Correct
What is the purpose of the diffusion model in DALL-E 2?
a. To convert images into text descriptions.

b. To generate images instantly from text descriptions.
c. To classify images based on text descriptions.
d. To gradually transform a random image into an image that matches the features.
Question 3
Correct
How does the generator in 3DFY.ai learn to generate 3D images closer to the prompt description?
a. Through generative adversarial networks (GANs)

b. Through unsupervised learning
c. Through reinforcement learning
d. Through supervised learning
https://trimestralexam.amaesonline.com/2323/mod/quiz/review.php?attempt=69542&cmid=14335 1/11
Question 4
Correct
What is the first step in processing a prompt by an LLM?
a. Breaking it down into individual words and phrases

b. Both A and B
c. Generating a response
d. None of the above
Question 5
Correct
What is the goal of prompt engineering?
a. To create prompts that are difficult for the model to understand.

b. To create prompts that are clear, concise, and effective.
c. To create prompts that confuse the AI generative models.
d. To create prompts that are unclear and ambiguous.
Question 6
Correct
What are prompts in the context of AI generative models?
a. Instructions that tell the model what to do.

b. Examples of creative content.
c. Negative words that confuse models.
d. Data used for training and evaluating prompts.
Question 7
Correct
How does DALL-E 2 generate images from text descriptions?
a. By using a technique called supervised learning.

b. By using a technique called reinforcement learning.
c. By using a technique called unsupervised learning.
d. By using a technique called diffusion modeling.
Question 8
Correct
What is the context of the prompt?
a. It helps the app to understand what you are asking for

b. None of the above
c. Both A and B
d. It confuses the app
Question 9
Correct
What are LLMs?
a. Both A and B
b. Large Language Models
c. Little Language Models
Question 10
Correct
What is the pattern used by an LLM to generate a response?
a. The pattern in the individual words and phrases of the prompt

b. Both A and B
c. The pattern in the dataset used to train the LLM
Question 11
Correct
What is the main challenge in prompt engineering?
a. Lack of data for training prompts.

b. Lack of experimentation.
c. Lack of a standard methodology.
d. Lack of AI generative models.
Question 12
Correct
What is the best way to learn how to improve prompts?
a. Experiment with different types of prompts

b. Use the same prompt over and over again
c. Both A and B
Question 13
Correct
What is the purpose of the provided references and supplementary materials in the document?
a. To provide additional resources for further learning

b. To showcase unrelated content
c. To advertise products and services
d. To list the names of the authors
Question 14
Correct
What type of artificial intelligence is used in 3DFY.ai to learn to create realistic outputs?
a. Unsupervised learning
b. Reinforcement learning
c. Generative adversarial networks (GANs)
d. Supervised learning
Question 15
Correct
What is the effect of using negative words in a prompt?
a. It confuses the app

b. None of the above
c. It helps the app to understand the prompt better
d. Both A and B
Question 16
Correct
What is the purpose of using examples in prompt engineering?
a. To provide context for the prompt.

b. To avoid experimentation.
c. To avoid using keywords.
d. To confuse the model.
Question 17
Correct
What is the recommended approach for writing a good prompt for 3DFY.ai?
a. Being specific and using keywords

b. Using vague language
c. Including negative words
d. Avoiding specific details
Question 18
Correct
What does the provided code do with the text description and the diffusion model?
a. Translates the text description into multiple languages

b. Generates the image
c. Analyzes the text description
d. Converts the text description into audio
Question 19
Correct
What is the primary focus of the reference material provided for Prompt Engineering for Text-Based Generative Art?
a. Techniques for writing effective prompts

b. Application of 3DFY.ai in product design
c. Reinforcement learning techniques
d. Use of GANs in 3D image generation
Question 20
Correct
What is the function of the gan_optimizer in the 3DFY.ai code snippet?
a. Evaluating the quality of 3D images

b. Updating the weights of the networks
c. Training the discriminator network
d. Generating 3D images
Question 21
Correct
What is the technique used by DALL-E 2 to ensure that the generated image is realistic and matches the text description?
a. LSTM
b. GAN
c. CLIP
d. LLM
Question 22
Correct
What is the main focus of prompt engineering?
a. To reduce the capabilities of AI generative models.

b. To create biased output.
c. To create prompts that are clear, concise, and effective.
d. To avoid developing new and innovative techniques.
Question 23
Correct
What is the purpose of the gan_train_step function in the 3DFY.ai code snippet?
a. Generating 3D images
b. Training the discriminator network
c. Updating the weights of the networks
d. Evaluating the quality of 3D images
Question 24
Correct
What is the primary technique used by 3DFY.ai to generate 3D models from text descriptions?
a. Unsupervised learning
b. Generative adversarial networks (GANs)
c. Reinforcement learning
d. Supervised learning
Question 25
Correct
What is DALL-E 2?
a. A video game.
b. A music streaming service.
c. A social media platform.
d. A large language model developed by OpenAI.
Question 26
Correct
What are prompts?
a. Patterns used to generate a response

b. Instructions given to an AI generative app
c. Both A and B
Question 27
Correct
What type of learning technique is used to train the neural network in DALL-E 2?
a. Supervised learning
b. Reinforcement learning
c. Unsupervised learning
d. Semi-supervised learning
Question 28
Correct
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 29
Correct
What is the role of the generator network in the 3DFY.ai code snippet?
a. Providing prompts for 3D image generation

b. Generating 3D images from prompts
c. Evaluating the quality of 3D images
d. Training the discriminator network
Question 30
Correct
What is the role of experimentation in prompt engineering?
a. To avoid trying different prompts.

b. To learn how to improve prompts.
c. To avoid improving the performance of AI generative models.
d. To use the same prompt repeatedly.
Question 31
Correct
What are the tips for improving prompts?
a. Avoid using negative words

b. Be clear and concise
c. Use keywords that are relevant to the task
d. Be specific about what you want the app to do
Question 32
Correct
What is the neural network used by DALL-E 2 to generate images?
a. CLIP
b. LLM
c. GAN
d. LSTM
Question 33
Correct
What is the importance of writing clear and concise prompts?
a. None of the above

b. To confuse the app
c. To get better results from the app
d. Both A and B
Question 34
Correct
What is the role of the discriminator in the 3DFY.ai model?
a. Providing prompts for 3D image generation

b. Evaluating the quality of 3D images
c. Generating 3D images
d. Training the generator network
Question 35
Correct
What is the potential application of DALL-E 2 mentioned in the document?
a. Creating cooking recipes

b. Creating weather forecasts
c. Creating music albums
d. Creating educational materials
Question 36
Correct
Why are keywords important in prompt engineering?
a. They help the model understand the task.

b. They are not important in prompt engineering.
c. They confuse the model.
d. They are used for negative prompts.
Question 37
Correct
What is the use of negative words in prompt engineering?
a. They are used for positive prompts.

b. They help the model understand the task.
c. They confuse the model.
d. They are not used in prompt engineering.
Question 38
Correct
What is the dataset used to train LLMs?
a. Massive datasets of text and code

b. Small datasets of text and code
c. None of the above
d. Both A and B
Question 39
Correct
What does the size of the GAN affect in 3DFY.ai?
a. The quality of the 3D images generated

b. The speed of 3D image generation
c. The number of prompts accepted
d. The type of GAN used
Question 40
Correct
What is the main responsibility of prompt engineers?
a. To reduce the capabilities of AI generative models.

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

AI

Uploaded by

Copyright:

Available Formats

AI

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AI

Uploaded by

Copyright:

Available Formats

3/1/24, 10:36 AM MIDTERM LAB EXAM: Attempt review

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

Started on Friday, 1 March 2024, 10:25 AM

Mark 1.00 out of 1.00

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

a. A model that can generate realistic images.

Mark 1.00 out of 1.00

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

a. To convert images into text descriptions.

Mark 1.00 out of 1.00

a. Through generative adversarial networks (GANs)

Mark 1.00 out of 1.00

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

a. Breaking it down into individual words and phrases

Mark 1.00 out of 1.00

What is the goal of prompt engineering?

a. To create prompts that are difficult for the model to understand.

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.

Mark 1.00 out of 1.00

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

a. By using a technique called supervised learning.

Mark 1.00 out of 1.00

What is the context of the prompt?

a. It helps the app to understand what you are asking for

Mark 1.00 out of 1.00

What are LLMs?

Mark 1.00 out of 1.00

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

a. The pattern in the individual words and phrases of the prompt

Mark 1.00 out of 1.00

What is the main challenge in prompt engineering?

a. Lack of data for training prompts.

Mark 1.00 out of 1.00

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

a. Experiment with different types of prompts

Mark 1.00 out of 1.00

a. To provide additional resources for further learning

Mark 1.00 out of 1.00

Mark 1.00 out of 1.00

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

a. It confuses the app

Mark 1.00 out of 1.00

What is the purpose of using examples in prompt engineering?

a. To provide context for the prompt.

Mark 1.00 out of 1.00

a. Being specific and using keywords

Mark 1.00 out of 1.00

a. Translates the text description into multiple languages

Mark 1.00 out of 1.00

a. Techniques for writing effective prompts

Mark 1.00 out of 1.00

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

a. Evaluating the quality of 3D images

Mark 1.00 out of 1.00

Mark 1.00 out of 1.00

What is the main focus of prompt engineering?

a. To reduce the capabilities of AI generative models.