Supervised learning uses target values or labels during training, while unsupervised learning looks for patterns without given target values.

Question

BlackTom AI · Accepted Answer

Supervised learning uses labeled examples (input-output pairs) so models can learn a mapping from inputs to explicit targets; unsupervised learning attempts to discover structure or patterns in unlabeled data.

1. Relevant knowledge points and concepts
- Supervised learning: training data includes input features X and target values y (labels). Common tasks: classification (discrete labels) and regression (continuous targets). Learning proceeds by minimizing a loss function that measures prediction error against the provided labels.
- Unsupervised learning: training data contains only inputs X without target y. Tasks focus on finding structure: clustering (group similar instances), dimensionality reduction (PCA, manifold learning), density estimation, or anomaly detection.
- Distinctions: supervised methods require labeled data and evaluate via accuracy/error on labels; unsupervised methods evaluate structure quality (e.g., silhouette score) or downstream use.

2. Step-by-step reasoning
- The statement says supervised learning uses target values/labels during training: by definition, supervised methods learn from labeled pairs (X,y). Example: training a classifier to map images to category labels.
- It says unsupervised learning looks for patterns without given target values: unsupervised methods operate on X alone to find clusters, latent factors, or low-dimensional representations.

3. Intermediate steps / calculations
- No numeric calculation is needed. Conceptually: supervised training minimizes loss L(f(X), y); unsupervised methods optimize objectives based solely on X (e.g., minimize within-cluster variance in k-means).

4. Why the correct answer is correct
- The definitions above directly match the statement: supervised = uses labels; unsupervised = no labels and finds structure. This is textbook machine learning terminology.

5. Why the other option is incorrect
- "False" would assert the definitions are wrong. Since the standard definitions align with the statement, "False" is incorrect.

6. Conclusion
The statement is True. This matches the provided answer: True.

Supervised learning uses target values or labels during training, while unsupervised learning looks for patterns without given target values.判断题

类似问题

Which example below lists only classic model families?

Learning types describe how a model learns based on the available data and learning signal, while model families describe what kind of algorithm or model is used.

Deep learning is a learning type, just like supervised learning and unsupervised learning.

Which example below lists only classic model families?

Question at position 26 Large Language Models typically require significantly less computational power than a Small Language Model as they are built in a more streamlined manner, and the models are typically more efficient.TrueFalse

Which of the following statements about machine learning is not true?

The concept of machine learning typically involves (check all that apply)

The concept of machine learning typically involves (check all that apply)

更多留学生实用工具

智能学习助手

风格化写作助手

论文查重助手

文献引用助手

课堂转译助手

课堂笔记助手

Quiz搜索助手

学校历年真题

智能刷题助手

智能匹配练习

希望你的学习变得更简单