What is Encoder-Decoder?
An AI architecture where one part compresses input into a representation and another part generates output from it.
Why It Matters
The encoder-decoder pattern is fundamental to translation, summarisation, and many other AI tasks.
Real-World Example
In translation, the encoder reads and understands the English sentence, then the decoder generates the French version.
“Understanding terms like Encoder-Decoder matters because it helps you have better conversations with developers and make smarter decisions about your software. You do not need to be technical. You just need to know enough to ask the right questions.”
Related Terms
Transformer
A type of AI architecture that processes text by paying attention to relationships between all words at once, rather than reading sequentially.
Cross-attention
A mechanism where one sequence of data attends to another, enabling models to connect different inputs.
Autoregressive Model
An AI model that generates output one piece at a time, using each piece to predict the next.
Learn More at buildDay Melbourne
Want to understand these concepts hands-on? Join our one-day workshop and build a real web application from scratch.
Related Terms
Transformer
A type of AI architecture that processes text by paying attention to relationships between all words at once, rather...
Cross-attention
A mechanism where one sequence of data attends to another, enabling models to connect different inputs.
Autoregressive Model
An AI model that generates output one piece at a time, using each piece to predict the next.
Large Language Model (LLM)
An AI system trained on massive amounts of text that can understand and generate human language.
Attention Mechanism
A technique that lets AI models focus on the most relevant parts of the input when generating output.
Tokenisation
The process of breaking text into smaller pieces called tokens that an AI model can process.