Generative AI, Transformer Models, and Large Language Models (LLMs) Exercises (Part 2)

Quiz Summary

0 of 6 Questions completed

Questions:

You have already completed the quiz before. Hence you can not start it again.

Quiz is loading…

You must sign in or sign up to start the quiz.

You must first complete the following:

Results

Quiz complete. Results are being recorded.

Results

0 of 6 Questions answered correctly

Your time:

You have reached 0 of 0 point(s), (0)

Current
Review
Answered
Correct
Incorrect

Question 1 of 6

1. Question

Match the Generative AI term to the definition

Sort elements

Generative AI
Transformer Models
Large Language Models (LLMs)
Foundation Models

Application of machine learning techniques to the creation of new data based on learned patterns

Deep learning model architecture that is designed to process sequential input data like Recurrent Neural Networks (RNNs), but unlike RNNs, uses the idea of self-attention to be able to process long strings of input without having to process each sequentially one at a time.

Models trained on large amounts of text that are configured to generate human understandable text from human provided input prompts.

Large, pre-trained models focused on a general set of tasks such as language or computer vision that make it easy to be adapted to domain-specific applications.

Question 2 of 6

2. Question
LLMs are proving to be incredibly useful for a variety of things including (select all that apply)
- Text summarization
- Translation
- Improve search quality
- Classify and categorize content
- Code generation
- Generate art
- Autonomous vehicles
Correct

Incorrect
Question 3 of 6

3. Question
Characteristics of a Foundation Model include (select all that apply):
- Pretrained using a large amount of data
- Foundational models generally have billions of parameters trained on petabytes of data
- Generalized in that the model can be used for a wide range of applications
- Can be applied to a wide range of domain-specific applications through fine-tuning or prompt-engineering
- Uses supervised learning approaches with labeled training data
- Ensemble of a variety of different models
Correct

Incorrect
Question 4 of 6

4. Question
You can directly use a Foundation model for specific applications.
- True
- False
Correct

Incorrect

Question 5 of 6

5. Question

Match the Foundation Model or LLM term to the definition

Sort elements

Self-Supervised Learning
OpenAI
Vector Database
Prompt Engineering
LangChain
ChatGPT

A form of machine learning where labels are automatically created from the input data.

An organization that has made notable contributions to advance the state of Artificial Intelligence including GPT-3, GPT-4, and DALL-E.

A means to store tokens processed in the embedding format expected by LLMs and are used to find content that is similar to your search query

Also referred to as “word coding”, it’s what you tell the Generative AI system to get the desired output

A framework tool for building LLM-based applications that are data-aware and agent-based

An application built on top of the GPT Foundation model that has been trained for conversational interaction with an LLM

Question 6 of 6

6. Question
ChatGPT was developed by which company?
- Microsoft
- OpenAI
- DeepMind
- Google
Correct

Incorrect