1.Prompt tuning is a technique for:
Making large language models more accurate.
Improving the output quality of large language models. 정답
Making large language models more versatile.
Training large language models.
2.Which are examples of tasks that Bard code generation can perform? (Select 3)
Detect emerging security vulnerabilities
Translate code from one language to another 정답
Debug your lines of source code 정답
Explain your code to you line by line 정답
3. What is a prompt?
A guide to write code in different programming languages
A natural language processing concept that involves text embeddings
A text to query or instruct a large language model (LLM) to generate desired output 정답
A pre-trained AI model to perform a variety of tasks
4.You are planning a trip to Germany in a few months. You’ve booked a hotel that includes dinner. You want to email the hotel so they are aware of your food preferences. Using gen AI, you can easily generate an email in German using English prompts. Which gen AI training model enables you to do this?
5.According to Google’s AI Principles, bias can enter into the system at only specific points in the ML lifecycle.
6. Your company has a large language model (LLM) to help employees with their everyday tasks. You want to teach your colleagues about prompt design. Which of the following is a good example of a well-designed prompt?
When does my manager expect me to complete my project?
What is the meaning of life?
Can you tell me how long a really long paragraph can be before it’s too long?
Translate the following sentence into French: Hello, how are you today? 정답
7.Google’s approach to responsible AI is based on which of the following commitments? (Select 4) 공부필요
It’s accountable and safe.
It eliminates team disagreements.
It speeds up product development processes.
It’s driven by scientific excellence.
8.Which of the following is a potential use of generative AI?
Automatic reading of X-rays
A customer service chatbot 정답
A robot that performs mechanical tasks
9.What are some benefits of prompt tuning? (Select 2)
Generalizes large language models’ (LLMs) commands to conduct versatile tasks
Enables large language models (LLMs) to be trained on small amounts of data
Enables large language models (LLMs) to adapt to a wide range of tasks 정답
Increases large language models’ (LLMs) production of unbiased responses
Helps large language models (LLMs) generate more accurate responses 정답
10.You want to explain to a colleague how gen AI works. Which of the following would be a good explanation?
Gen AI randomly generates new content without any input from existing data.
Gen AI learns from existing data and then creates new content that is similar to the data it was trained on. 정답
Gen AI uses a set of rules to generate new content that is always unique and original.
Gen AI determines the relationship between datasets and classifies data according to existing data sets.
11. You want to use machine learning to discover the underlying pattern and group a collection of unlabeled photos into different sets. Which should you use?
Large language models (LLM)
12. Which of the following are examples of pre-training for a large language model (LLM)? (Select 3)
Document summarization 정답
13.Which of the following is recommended by Google as most important in establishing AI governance?
Developing technical tools to evaluate ML models
Encouraging people to make decisions based on their own values
Creating decision trees to address common ethical situations
Building practices around ethical decision-making 정답
14.How does generative AI work?
It uses a neural network to learn from a large dataset. 정답
It uses the internet to repeat answers for common questions.
It uses a generic algorithm to evolve a population of models until it finds one that can generate the desired output.
It uses a rule-based system to generate output based on a set of predefined rules.
15.You want to organize documents into distinct groups, without predefining the groups. Which type of machine learning model should you use?
Discriminative deep learning model
Supervised learning model
Natural language processing (NLP) model
Unsupervised learning model 정답
16.What is machine learning?
Algorithms used to describe and create new data
Programs or systems that learn from data instead of being explicitly programmed 정답
Large, general purpose language models
Artificial intelligence technology that can produce various types of content
17. What are the elements of a transformer model at a high-level?
Supervised and unsupervised
Generative and predictive
18.The performance of large language models (LLMs) generally improves as more data and parameters are added.
19.What action does Google recommend organizations take to ensure that AI is used responsibly?
Use a checklist to evaluate responsible AI
Follow a top-down approach to increase AI adoption
Seek participation from a diverse range of people 정답
20.Most organizations have the capability to train large language models (LLMs) from scratch.