AI glossary
What is transformer?
Short answer
A neural network architecture built on attention, used by virtually all modern LLMs.
For example
GPT stands for Generative Pre-trained Transformer. The same architecture also powers translation tools and many image models.
Learn it in a free lesson
- Using AI wisely: privacy, bias, judgementBeginner · 5 min
- Seeing and hearing: multimodal modelsIntermediate · 6 min
- Seeing and remembering: CNNs & RNNsIntermediate · 7 min
- Diffusion: art from noiseAdvanced · 6 min
- Attention is all you needAdvanced · 8 min
- Mixture of experts: big models, small billsAdvanced · 8 min
Related terms
Questions
What is transformer in simple terms?
A neural network architecture built on attention, used by virtually all modern LLMs.
What is an example of transformer?
GPT stands for Generative Pre-trained Transformer. The same architecture also powers translation tools and many image models.
Where can I learn about transformer for free?
AI in Bed explains it in the free lesson "Using AI wisely: privacy, bias, judgement" (Beginner level, 5 minutes), with no sign-up.