CS7643 QUIZ 4 EXAM WITH CORRECT QUESTIONS AND ANSWERS 2025

CS7643 QUIZ 4 EXAM WITH CORRECT
QUESTIONS AND ANSWERS 2025


Embedding - CORRECT-ANSWERSA learned map from entities to vectors that encodes



similarity



Graph Embedding - CORRECT-ANSWERSOptimize the objective that connected nodes have



more similar embeddings than unconnected nodes.




Task: convert nodes to vectors




- effectively unsupervised learning where nearest neighbors are similar



- these learned vectors are useful for downstream tasks



Multi-layer Perceptron (MLP) pain points for NLP - CORRECT-ANSWERS- Cannot easily



support variable-sized sequences as inputs or outputs

,- No inherent temporal structure



- No practical way of holding state



- The size of the network grows with the maximum allowed size of the input or output



sequences



Truncated Backpropagation through time - CORRECT-ANSWERS- Only backpropagate a RNN



through T time steps



Recurrent Neural Networks (RNN) - CORRECT-ANSWERSh(t) = activation(U*input + V*h(t-1)



+ bias)



y(t) = activation(W*h(t) + bias)




- activation is typically the logistic function or tanh



- outputs can also simply be h(t)



- family of NN architectures for modeling sequences

, Training Vanilla RNN's difficulties - CORRECT-ANSWERS- Vanishing gradients



- Since dx(t)/dx(t-1) = w^t



- if w > 1: exploding gradients



- if w < 1: vanishing gradients



Long Short-Term Memory Network Gates and States - CORRECT-ANSWERS- f(t) = forget



gate



- i(t) = input gate



- u(t) = candidate update gate



- o(t) = output gate




- c(t) = cell state



- c(t) = f(t) * c(t - 1) + i(t) * u(t)