Chilfox

  • Related Notes
  • Three Ways of Processing Sequences
  • RNN
  • 1D Convolution
  • Self-Attention
Home

❯

DL4CV

❯

notes

❯

D DL4CV Lec13f SequenceProcessingComparison

D-DL4CV-Lec13f-SequenceProcessingComparison

Type
digest
Aliases
Comparison between Three Sequence Processing Method
Source Link
D-DL4CV-Lec13-Transformers

Related Notes

  • D-DL4CV-Lec07-ConvolutionalNetwork
  • D-DL4CV-Lec12-RecurrentNeuralNetwork
  • D-DL4CV-Lec13-Transformers

Three Ways of Processing Sequences

RNN

Pros:

  • Good at processing long sequences

Cons:

  • Not parallelizable, need to compute hidden states sequentially

1D Convolution

Pros:

  • Highly parallelizable

Cons:

  • Bad at dealing long sequences

Self-Attention

Pros:

  • Good at processing long sequences
  • Highly parallel

Cons:

  • Very memory extensive

關係圖譜

反向連結

  • D-DL4CV-Lec13-Transformers
  • D-DL4CV-Lec18g-self-attention

Created with Quartz v4.5.1 © 2026