AWS Certified AI Practitioner417 questions across 42 pages are complete and free, with no account or card.
417 questions in this bank
Free access · progress saved on this device
A company needs to use Amazon SageMaker for model training and inference. The company must comply with regulatory requirements to run SageMaker jobs in an isolated environment without internet access. Which solution will meet these requirements?
Answer: B
An ML research team develops custom ML models. The model artifacts are shared with other teams for integration into products and services. The ML team retains the model training code and data. The ML team wants to build a mechanism that the ML team can use to audit models. Which solution should the ML team use when publishing the custom ML models?
Answer: C
Amazon SageMaker Model Cards: These provide a standardized way to document important information about ML models, including: Model purpose and intended use cases Training data and methodology Evaluation metrics and results Ethical considerations and limitations Bias analysis Version history This comprehensive documentation facilitates auditing by providing a clear record of how the model was developed, evaluated, and intended to be used. It also promotes transparency and accountability. B. Use AWS AI Service Cards for transparency and understanding models: AWS AI Service Cards are designed for pre-built AI services provided by AWS, not for custom ML models developed by a team. They are not applicable for this use case.
Source: Adapted from community discussion — Moon
A software company builds tools for customers. The company wants to use AI to increase software development productivity. Which solution will meet these requirements?
Answer: B
Code Recommendation Software: Code recommendation software, such as Amazon CodeWhisperer or similar tools, integrates directly into developer environments (e.g., IDEs). These tools use machine learning and AI to: Suggest code snippets. Autocomplete code based on context. Improve developer productivity by reducing the time spent writing repetitive or boilerplate code.
Source: Adapted from community discussion — KevinKas
A retail store wants to predict the demand for a specific product for the next few weeks by using the Amazon SageMaker DeepAR forecasting algorithm. Which type of data will meet this requirement?
Answer: C
DeepAR and Time Series Data: The Amazon SageMaker DeepAR forecasting algorithm is specifically designed to handle time series data for forecasting tasks. Time series data consists of observations collected at regular intervals over time (e.g., daily sales of a product). DeepAR uses historical patterns in this data to predict future values. Why Time Series Data is Required: To predict product demand, the model needs past sales data (e.g., daily, weekly, or monthly), which is inherently time series data.
Source: Adapted from community discussion — KevinKas
A large retail bank wants to develop an ML system to help the risk management team decide on loan allocations for different demographics. What must the bank do to develop an unbiased ML model?
Answer: D
D. Measure class imbalance on the training dataset. Adapt the training process accordingly: This is the correct answer. Class imbalance occurs when one class (e.g., loan approval) is significantly more represented in the training data than another. This can lead to biased models that favor the majority class. Measuring and addressing class imbalance (e.g., through resampling or weighting techniques) is crucial for building fair models. Why not B? B. Ensure that the ML model predictions are consistent with historical results: If historical results reflect existing biases in lending practices, ensuring consistency with them will simply perpetuate those biases. This is the opposite of what is desired.
Source: Adapted from community discussion — Moon
Which prompting technique can protect against prompt injection attacks?
Answer: A
The most effective technique for protecting against prompt injection attacks is A. Adversarial Prompting. Here's why: Proactive Defense: Adversarial prompting involves deliberately crafting malicious prompts to test the model's boundaries and identify vulnerabilities. This proactive approach helps uncover weaknesses that might otherwise go unnoticed. While C. Least-to-most Prompting can indirectly improve robustness by simplifying the initial prompts, it's not a primary defense against prompt injection. Its primary focus is on improving task completion, not directly addressing malicious inputs. Key takeaway: Adversarial prompting is the most direct and effective method for enhancing the security of language models against prompt injection attacks.
Source: Adapted from community discussion — aws_Tamilan
A company has fine-tuned a large language model (LLM) to answer questions for a help desk. The company wants to determine if the fine-tuning has enhanced the model's accuracy. Which metric should the company use for the evaluation?
Answer: C
The F1 score is a widely used metric for evaluating the accuracy of a model, especially in classification tasks where there is an imbalance between precision and recall. It is the harmonic mean of precision and recall, providing a balanced measure of the model’s ability to correctly identify relevant information while minimizing false positives and false negatives. In the context of a help desk model, you want to measure both the precision (correctness of answers) and recall (how well the model retrieves the relevant information). The F1 score helps you achieve a balanced view of these two metrics, making it a good choice for evaluating model accuracy in a fine-tuned large language model (LLM) for answering questions.
Source: Adapted from community discussion — Jessiii
A company is using Retrieval Augmented Generation (RAG) with Amazon Bedrock and Stable Diffusion to generate product images based on text descriptions. The results are often random and lack specific details. The company wants to increase the specificity of the generated images. Which solution meets these requirements?
Answer: C
A company wants to implement a large language model (LLM) based chatbot to provide customer service agents with real-time contextual responses to customers' inquiries. The company will use the company's policies as the knowledge base. Which solution will meet these requirements MOST cost-effectively?
Answer: C
A company wants to create a new solution by using AWS Glue. The company has minimal programming experience with AWS Glue. Which AWS service can help the company use AWS Glue?
Answer: A
Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page
AIF-C01 practice, question 141. 417 questions available.
Version 1.0.0. How we source questions