data_mining:neural_network:sequences:recurrentnn

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
data_mining:neural_network:sequences:recurrentnn [2019/10/26 10:09] – ↷ Page moved from data_mining:neural_network:recurrentnn to data_mining:neural_network:sequences:recurrentnn phreazerdata_mining:neural_network:sequences:recurrentnn [2020/05/29 16:23] (current) – [Vanishing gradient] phreazer
Line 77: Line 77:
  
 Problem: Problem:
-Not very good at capturing long-term dependencies (single/plural subjects and verbs). Stronger influenced by nearby variables.+Not very good at capturing long-term dependencies (single/plural subjects and verbs). **Stronger influenced by nearby variables**.
  
 Exploding gradients can happen, but easier to spot => NAN. Exploding gradients can happen, but easier to spot => NAN.
  • data_mining/neural_network/sequences/recurrentnn.1572084546.txt.gz
  • Last modified: 2019/10/26 10:09
  • by phreazer