Glossary
Short, plain-language definitions of the AI/ML terms I keep bumping into. Each entry is one tight paragraph with links to related terms. Use the filter to jump straight to one.
No terms match that.
Core concepts
- AGIHypothetical AI that matches humans across essentially all intellectual tasks — a contested, moving goalpost.
- DimensionsIndependent axes of variation; ML vectors live in hundreds or thousands of them.
- EmbeddingsDense vectors where distance & direction encode meaning — the backbone of semantic search and RAG.
- Latent spaceThe hidden vector space where geometry encodes meaning.
- LoRALow-rank adapters; parameter-efficient fine-tuning.
- Machine learningSystems that learn patterns from data instead of hand-written rules.
- ParametersLearned weights; the count is model size & memory cost.
- TensorN-dimensional numeric array; the core ML data structure.
- Validation lossHeld-out validation error; the overfitting tripwire.