Symbolic AI (good old-fashioned AI)

AI built from explicit symbols, logic rules, and structured knowledge: often contrasted with numeric learning from raw data.

Symbolic AI (also GOFAI, “good old-fashioned AI”) encodes intelligence as manipulation of symbols and rules: theorem proving, planners, semantic nets, expert-system rule bases. Strengths include interpretability where rules apply: and brittleness when real-world noise breaks assumptions.

Historical AI winters partly reflected limits of purely symbolic pipelines compared with later machine learning and especially deep learning.