Transformer

YouTube search... ...Google search

• Sequence to Sequence (Seq2Seq)
• Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)
• Autoencoders / Encoder-Decoders
• Natural Language Processing (NLP)

“Attend” to specific parts of the input (an image or text) in sequence, one after another. By relying on a sequence of glances, they capture (visual) structure, can be contrasted with other (machine vision) techniques that process a whole input e.g. image in a single, forward pass.