Prerequisites: Recurrent Neural Networks, Long Short Term Memory Networks
To solve the Vanishing-Exploding gradients problem often encountered during the operation of a basic Recurrent Neural Network, many variations were developed. One of the most famous variations is the Long Short Term Memory Network(LSTM). One of the lesser known but equally effective variations is the Gated Recurrent Unit Network(GRU).
Unlike LSTM, it consists of only three gates and does not maintain an Internal Cell State. The information which is stored in the Internal Cell State in an LSTM recurrent unit is incorporated into the hidden state of the Gated Recurrent Unit. This collective information is passed onto the next Gated Recurrent Unit. The different gates of a GRU are as described below:-
- Update Gate(z): It determines how much of the past knowledge needs to be passed along into the future. It is analogous to the Output Gate in an LSTM recurrent unit.
- Reset Gate(r): It determines how much of the past knowledge to forget. It is analogous to the combination of the Input Gate and the Forget Gate in an LSTM recurrent unit.
- Current Memory Gate(): It is often overlooked during a typical discussion on Gated Recurrent Unit Network. It is incorporated into the Reset Gate just like the Input Modulation Gate is a sub-part of the Input Gate and is used to introduce some non-linearity into the input and to also make the input Zero-mean. Another reason to make it a sub-part of the Reset gate is to reduce the effect that previous information has on the current information that is being passed into the future.
The basic work-flow of a Gated Recurrent Unit Network is similar to that of a basic Recurrent Neural Network when illustrated, the main difference between the two is in the internal working within each recurrent unit as Gated Recurrent Unit networks consist of gates which modulate the current input and the previous hidden state.
Working of a Gated Recurrent Unit:
- For each gate, calculate the parameterized currrent input and previous hidden state vectors by performing element-wise multiplication (hadmard product) between the concerned vector and the respective weights for each gate.
- Apply the respective activation function for each gate element-wise on the parameterized vectors. Below given is the list of the gates with the activation function to be applied for the gate.
Update Gate : Sigmoid Function Reset Gate : Sigmoid Function
The above stated working is stated as below:-
Note that the blue circles denote element-wise multiplication. The positive sign in the circle denotes vector addition while the negative sign denotes vector subtraction(vector addition with negative value).The weight matrix W contains different weights for the current input vector and the previous hidden state for each gate.
Just like Recurrent Neural Networks, a GRU network also generates an output at each time step and this output is used to train the network using gradient descent.
Note that just like the workflow, the training process for a GRU network is also diagramatically similar to that of a basic Recurrent Neural Network and differs only in the internal working of each recurrent unit.
The Back-Propagation Through Time Algorithm for a Gated Recurrent Unit Network is similar to that of a Long Short Term Memory Network and differs only in the differential chain formation.
Let be the predicted output at each time step and be the actual output at each time step. Then the error at each time step is given by:-
The total error is thus given by the summation of errors at all time steps.
Similarly, the value can be calculated as the summation of the gradients at each time step.
Using the chain rule and using the fact that is a function of and which indeed is a function of , the following expression arises:-
Thus the total error gradient is given by the following:-
Note that the gradient equation involves a chain of which looks similar to that of a basic Recurrent Neural Network but this equation works differently because of the internal workings of the derivatives of .
How do Gated Recurrent Units solve the problem of vanishing gradients?
The value of the gradients is controlled by the chain of derivatives starting from . Recall the expression for :-
Using the above expression, the value for is:-
Recall the expression for :-
Using the above expression to calculate the value of :-
Since both the update and reset gate use the sigmoid function as their activation function, both can take values either 0 or 1.
Case 1(z = 1):
In this case, irrespective of the value of , the term is equal to z which in turn is equal to 1.
Case 2A(z=0 and r=0):
In this case, the term is equal to 0.
Case 2B(z=0 and r=1):
In this case, the term is equal to . This value is controlled by the weight matrix which is trainable and thus the network learns to adjust the weights in such a way that the term comes closer to 1.
Thus the Back-Propagation Through Time algorithm adjusts the respective weights in such a manner that the value of the chain of derivatives is as close to 1 as possible.