Question$-2$:

Take the detect$\_$names$\_$lstm$.$ipynb example. Change network architecture as follows:

Use an LSTM layer with hidden dimension $=64$

Use tanh nonlinearity

Use linear transformation that transforms features to $32$ dimensions.

Use another LSTM layer with hidden dimension $=64$

Use another linear transformation $($you decide what the output dimension should be$)$

Use softmax

Train your network. Plot the loss function using tensorboard.

Solve this question in python. Also use pytorch not keras