AI Foundationsbeginner11 min · 9 steps
Symbolic AI and Expert Systems
Before machine learning, AI meant writing knowledge down as symbols and rules and letting an inference engine reason over them — an approach that still earns its place wherever decisions must be explained.
dataresponserequesterror
Key ideaStep 1 of 9
Intelligence as symbol manipulation
Symbolic AI — often called GOFAI, Good Old-Fashioned AI — represents knowledge explicitly as symbols (power_fault, battery_ok) and rules, then applies logical inference to reach conclusions.
Machine learning goes the other way: it learns patterns from examples and stores them as numbers in weights. Symbolic AI was the dominant approach in early AI research, and it is still used where reasoning must be explicit, checkable and explainable.
| Machine learning | Symbolic AI | |
|---|---|---|
| Knowledge comes from | Training data | Experts, written as rules |
| Stored as | Weights | Symbols and rules |
| Explains a decision | Hard (black box) | Natively (rule trace) |
| Handles the unforeseen | Generalises (sometimes) | Only if a rule covers it |
InsightSymbolic AI doesn't learn the answer — it derives it from knowledge someone wrote down.
Lesson 12 of 34 in AI Foundations