ARTiBA Start Focus
Log In Create Account

AIF-C01 workspace

Detailed Explanations

A detailed answer review with side-by-side rationale, distractor analysis, related questions, and weak-topic practice.

Certification
Build Quiz

AIF-C01 catalog review

Modern Learning Paradigms

Correct: A
Your answer Not answered Answer this in practice or the daily question to sync here.
Correct answer A The model creates proxy labels from unlabeled data, such as predicting masked tokens.
Result Awaiting answer Synced from this browser when available.
Confidence Unset Use the practice page confidence controls to calibrate this item.

Which description best defines self-supervised learning?

A The model creates proxy labels from unlabeled data, such as predicting masked tokens.
B The model clusters records only by distance and never optimizes a predictive objective.
C The model learns only from human-labeled input-output pairs for the target task.
D The model chooses actions in an environment and improves from delayed rewards.
1. Answer captured 2. Key checked 3. Rationale review 4. Retry weak topic

Detailed explanation

Catalog rationale

Correct answer: A

Self-supervised learning is valuable when unlabeled data is abundant because the model can learn useful representations before supervised fine-tuning.

Key concept Modern Learning Paradigms

Artificial Intelligence Engineer - AiE

Exam tip Map the requirement to the managed ARTiBA capability.

Eliminate services that solve infrastructure, data movement, or routing when the stem asks for AI model access or governance.

ARTiBA service references

01 Artificial Intelligence Engineer - AiE 01 Foundational AI-ML Theory 01 Modern Learning Paradigms Artificial Intelligence Engineer - AiE

Why the wrong answers are wrong

B

Incorrect. Clustering is unsupervised, but it does not necessarily train a model to predict proxy targets.

C

Incorrect. Learning only from labeled input-output pairs describes supervised learning.

D

Incorrect. Learning from actions and rewards describes reinforcement learning.