Breaking News: Grepper is joining You.com. Read the official announcement!

Backpropagation in LSTM

Sleepy Starling answered on March 15, 2022 Popularity 7/10 Helpfulness 1/10

answer Backpropagation in LSTM

Backpropagation in LSTM

Comment

Let the gradient pass down by the above cell be: 
      E_delta  = dE/dht   
      
      If we are using MSE (mean square error)for error then,
      E_delta=(y-h(x))
      Here y is the original value and h(x) is the predicted value.     
              
  Gradient with respect to output gate  
          
             dE/do = (dE/dht ) * (dht /do) = E_delta * ( dht / do) 
                dE/do =  E_delta * tanh(ct) 
      
  Gradient with respect to ct         
      dE/dct = (dE / dht )*(dht /dct)= E_delta *(dht /dct) 
                dE/dct  =   E_delta   * o * (1-tanh2 (ct))        

  Gradient with respect to input gate dE/di, dE/dg 
           
      dE/di = (dE/di ) * (dct / di)  
             dE/di =  E_delta   * o * (1-tanh2 (ct)) * g 
      Similarly,  
      dE/dg =  E_delta   * o * (1-tanh2 (ct)) * i 
       
  Gradient with respect to forget gate  
           
          dE/df =  E_delta   * (dE/dct ) * (dct / dt) t
          dE/df =  E_delta   * o * (1-tanh2 (ct)) *  ct-1  

  Gradient with respect to ct-1  
           
          dE/dct =  E_delta   * (dE/dct ) * (dct / dct-1) 
          dE/dct =  E_delta   * o * (1-tanh2 (ct)) * f  
 
  Gradient with respect to output gate weights:
    
    dE/dwxo   =  dE/do *(do/dwxo) = E_delta * tanh(ct) * sigmoid(zo) * (1-sigmoid(zo) * xt
    dE/dwho   =  dE/do *(do/dwho) = E_delta * tanh(ct) * sigmoid(zo) * (1-sigmoid(zo) * ht-1
    dE/dbo   =  dE/do *(do/dbo) = E_delta * tanh(ct) * sigmoid(zo) * (1-sigmoid(zo)

   Gradient with respect to forget gate weights:
    
    dE/dwxf  =  dE/df *(df/dwxf) = E_delta * o * (1-tanh2 (ct)) * ct-1 * sigmoid(zf) * (1-sigmoid(zf) * xt
    dE/dwhf =  dE/df *(df/dwhf) = E_delta * o * (1-tanh2 (ct)) *  ct-1 * sigmoid(zf) * (1-sigmoid(zf) * ht-1
    dE/dbo  =  dE/df *(df/dbo) = E_delta * o * (1-tanh2 (ct)) *  ct-1 * sigmoid(zf) * (1-sigmoid(zf) 

   Gradient with respect to input gate weights:
    
    dE/dwxi  =  dE/di *(di/dwxi) = E_delta * o * (1-tanh2 (ct)) * g * sigmoid(zi) * (1-sigmoid(zi) * xt
    dE/dwhi =  dE/di *(di/dwhi) = E_delta * o * (1-tanh2 (ct)) * g * sigmoid(zi) * (1-sigmoid(zi) * ht-1
    dE/dbi  =  dE/di *(di/dbi) = E_delta * o * (1-tanh2 (ct)) * g *  sigmoid(zi) * (1-sigmoid(zi)
    
    dE/dwxg  =  dE/dg *(dg/dwxg) = E_delta * o * (1-tanh2 (ct)) * i * (1?tanh2(zg))*xt
    dE/dwhg  =  dE/dg *(dg/dwhg) = E_delta * o * (1-tanh2 (ct)) * i * (1?tanh2(zg))*ht-1
    dE/dbg  =  dE/dg *(dg/dbg)  = E_delta * o * (1-tanh2 (ct)) * i * (1?tanh2(zg))

Popularity 7/10 Helpfulness 1/10 Language whatever

Source: www.geeksforgeeks.org

Tags: backpropagation lstm whatever

Link to this answer
Share Copy Link

Contributed on Mar 15 2022

Sleepy Starling

0 Answers Avg Quality 2/10

Backpropagation in LSTM

Contents

More Related Answers

Backpropagation in LSTM

Grepper

Documentation

Social

Legal

Contact

Oops, You will need to install Grepper and log-in to perform this action.