AWS Certified AI PractitionerAI/ML and Generative AI FundamentalsEasy
A data scientist is preparing a dataset for an image classification task where the goal is to identify different species of birds from photographs. Each image in the dataset is associated with a specific bird species, such as 'Bald Eagle', 'Cardinal', or 'Blue Jay'. Which key AI/ML concept defines these specific bird species labels that the model will learn to predict?
- ALabel
- BFeature
- CAttribute
- DInstance
Show answer & explanationAnswer & explanation
Correct answer: A. Label
In supervised learning, the 'label' is the target variable or the output that the model is trained to predict. In this classification task, the 'specific bird species' ('Bald Eagle', 'Cardinal') are the labels associated with each image that the model learns to identify.
Why the other options are wrong
- B. A feature is an input variable used to make predictions (e.g., pixel values of the image), not the output itself.
- C. An attribute is synonymous with a feature, representing a characteristic or property of an instance, not the target prediction.
- D. An instance (or example/sample) refers to a single data point in the dataset (e.g., one bird photograph), not the predicted category.
Label (Supervised Learning)
In supervised machine learning, a label is the target variable or the 'correct answer' that the model is trained to predict for a given input. For classification tasks, labels are discrete categories.
- The 'correct answer' for input.
- Target variable in supervised learning.
- Discrete categories for classification.
Memory trick: Labeled data teaches smart models.