Standard 11 stops to get here · leads to 3

Encoder-Decoder

A architecture where the encoder processes input and the decoder generates output, used in translation and sequence-to-sequence tasks.

Your route here

11 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  3. Recurrent Neural Network ✓ understood

    A neural network architecture with loops that allow information to persist, designed for sequential data like text and time series.

  4. Sequence-to-Sequence ✓ understood

    Models that transform input sequences to output sequences, used for translation, summarization, and generation.

  5. Dataset ✓ understood

    A collection of data examples used for training, validating, or testing machine learning models.

  6. Feature ✓ understood

    A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model.

  7. Deep Learning ✓ understood

    A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

  8. Representation Learning ✓ understood

    Learning useful features or representations of data automatically, rather than hand-crafting them.

  9. Embedding ✓ understood

    A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together.

  10. Attention Mechanism ✓ understood

    A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step.

  11. Transformer ✓ understood

    A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model.

  12. Encoder-Decoder · you are here ✓ understood

Where it sits

Before this

Sequence-to-Sequence Transformer
Encoder-Decoder

Leads to

T5 U-Net BART

Explore nearby

Language & LLMs T5 Text-to-Text Transfer Transformer - frames all NLP tasks as text-to-text problems using a unified encoder-decoder architecture. Language & LLMs BART Bidirectional and Auto-Regressive Transformer - combines BERT-like encoder with GPT-like decoder for sequence-to-sequence tasks. Language & LLMs Cross-Attention Attention between two different sequences, where queries come from one and keys/values from another. Language & LLMs Encoder-Only Model A transformer with only encoder layers and bidirectional attention, suited for understanding tasks (BERT family). Language & LLMs Decoder-Only Model A transformer architecture with only decoder layers, using causal masking for autoregressive generation (GPT family).

In the research

All papers →

2 papers that build on Encoder-Decoder .