A company has documents that are missing some words because of a database error. The company wants to build an ML model that can suggest potential words to fill in the missing text. Which type of model meets this requirement?
Correct Answer: C
Question 52
A company wants to build a lead prioritization application for its employees to contact potential customers. The application must give employees the ability to view and adjust the weights assigned to different variables in the model based on domain knowledge and expertise. Which ML model type meets these requirements?
Correct Answer: A
The company needs an ML model for a lead prioritization application where employees can view and adjust the weights assigned to different variables based on domain knowledge. Logistic regression is a linear model that assigns interpretable weights to input features, making it easy for users to understand and modify these weights. This interpretability and adjustability make it suitable for the requirements. Exact Extract from AWS AI Documents: From the AWS AI Practitioner Learning Path: "Logistic regression is a supervised learning algorithm used for classification tasks. It is highly interpretable, as it assigns weights to each feature, allowing users to understand and adjust the importance of different variables based on domain expertise." (Source: AWS AI Practitioner Learning Path, Module on Machine Learning Algorithms) Detailed Explanation: * Option A: Logistic regression modelThis is the correct answer. Logistic regression provides interpretable coefficients (weights) for each feature, enabling employees to view and adjust them based on domain knowledge, meeting the application's requirements. * Option B: Deep learning model built on principal componentsDeep learning models, even when using principal components, are complex and lack interpretability. The weights in such models are not easily adjustable by users, making this option unsuitable. * Option C: K-nearest neighbors (k-NN) modelk-NN is a non-parametric model that does not assign explicit weights to features. It relieson distance metrics, which are not easily adjustable based on domain knowledge, so it does not meet the requirements. * Option D: Neural networkNeural networks are highly complex and lack interpretability, as their weights are not directly tied to input features in a human-understandable way. Adjusting weights based on domain knowledge is impractical, making this option incorrect. References: AWS AI Practitioner Learning Path: Module on Machine Learning Algorithms Amazon SageMaker Developer Guide: Logistic Regression (https://docs.aws.amazon.com/sagemaker/latest/dg /algos.html) AWS Documentation: Interpretable Machine Learning Models (https://aws.amazon.com/machine-learning/)
Question 53
An AI practitioner is using a large language model (LLM) to create content for marketing campaigns. The generated content sounds plausible and factual but is incorrect. Which problem is the LLM having?
Correct Answer: A
Question 54
A company needs to build its own large language model (LLM) based on only the company's private data. The company is concerned about the environmental effect of the training process. Which Amazon EC2 instance type has the LEAST environmental effect when training LLMs?
Correct Answer: D
The Amazon EC2 Trn series (Trainium) instances are designed for high-performance, cost-effective machine learning training while being energy-efficient. AWS Trainium-powered instances are optimized for deep learning models and have been developed to minimize environmental impact by maximizing energy efficiency. * Option D (Correct): "Amazon EC2 Trn series": This is the correct answer because the Trn series is purpose-built for training deep learning models with lower energy consumption, which aligns with the company's concern about environmental effects. * Option A: "Amazon EC2 C series" is incorrect because it is intended for compute-intensive tasks but not specifically optimized for ML training with environmental considerations. * Option B: "Amazon EC2 G series" (Graphics Processing Unit instances) is optimized for graphics- intensive applications but does not focus on minimizing environmental impact for training. * Option C: "Amazon EC2 P series" is designed for ML training but does not offer the same level of energy efficiency as the Trn series. AWS AI Practitioner References: * AWS Trainium Overview: AWS promotes Trainium instances as their most energy-efficient and cost- effective solution for ML model training.
Question 55
An AI practitioner has a database of animal photos. The AI practitioner wants to automatically identify and categorize the animals in the photos without manual human effort. Which strategy meets these requirements?
Correct Answer: A
Object detection is the correct strategy for automatically identifying and categorizing animals in photos. * Object Detection: * A computer vision technique that identifies and locates objects within an image and assigns them to predefined categories. * Ideal for tasks such as identifying animals in photos, where the goal is to detect specific objects (animals) and categorize them accordingly. * Why Option A is Correct: * Automatic Identification: Object detection models can automatically identify different types of animals in the images without manual intervention. * Categorization Capability: Assigns labels to detected objects, fulfilling the requirement for categorizing animals. * Why Other Options are Incorrect: * B. Anomaly detection: Identifies outliers or unusual patterns, not specific objects in images. * C. Named entity recognition: Used in NLP to identify entities in text, not for image processing. * D. Inpainting: Used for filling in missing parts of images, not for detecting or categorizing objects.
