人工智慧基礎

• Explain training and inference in plain language.
• Separate demonstrated capability from marketing claims.
• Evaluate AI outputs using evidence, uncertainty, and fit-for-purpose tests.

Prerequisites:None.

1. 1

   What AI is

   結果： Distinguish AI, machine learning, and ordinary software.

   練習： Classify five everyday systems and explain which definition of AI you used.

   AI concepts and boundaries
   什麼是人工智慧？ →機器學習基礎知識 →
2. 2

   How systems learn

   結果： Describe the role of examples, objectives, and generalization.

   練習： Diagnose why a model can perform well in testing but fail for a new population.

   Data, training, and generalization
   人工智慧如何學習 →機器學習基礎知識 →人工智慧培訓 →
3. 3

   Models and inference

   結果： Explain what happens when a trained model produces an output.

   練習： Trace one user request from input through model output and human review.

   模型、推論與限制
   人工智慧模型解釋 →人工智慧推理 →神經網路 →
4. 4

   Evidence and uncertainty

   結果： Check claims, benchmarks, and confident-sounding outputs.

   練習： Create a claim ledger for one AI product announcement.

   評估與基準素養Uncertainty and confidence calibration來源與主張驗證
   人工智慧基準 →人工智慧幻覺 →人工智慧神話 →