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
Next revisionBoth sides next revision
data_mining:neural_network:recurrentnn [2018/06/09 00:00] – [Bidirektional RNN] phreazerdata_mining:neural_network:recurrentnn [2018/06/09 00:12] – [Bidirektional RNN] phreazer
Line 133: Line 133:
  
 Take info from sequence on the right Take info from sequence on the right
 +
 +Going forward to last unit and back from there; Acyclic graph, two activations per step (forward, backward).
 +
 +Activation blocks can be GRU or LSTM
 +
 +===== Deep RNN =====
 +
 +
  • data_mining/neural_network/sequences/recurrentnn.txt
  • Last modified: 2020/05/29 18:23
  • by phreazer