Modify this PyTorch pseudo-code to perform negative sampling if the pos_ids are known: label #shape=[batch_s, pos_ids] hidden #shape=[batch_s, ch] logits #shape=[ch, C] out=np.dot(logits, hidden(X)) #shape=[batch_s, C] loss=cross_entropy(out, label)

Execution
Top-Interview
Hard
45 min

What this question tests

Execution
Structured problem solving
Communication
Trade-off reasoning

Practise this question under interview conditions. Answer it out loud against a timer with an AI interviewer that asks follow-ups, then review the scored report.

Start a timed mock interview

Modify this PyTorch pseudo-code to perform negative sampling if the pos_ids are known: label #shape=[batch_s, pos_ids] hidden #shape=[batch_s, ch] logits #shape=[ch, C] out=np.dot(logits, hidden(X)) #shape=[batch_s, C] loss=cross_entropy(out, label)

What this question tests

Related Execution questions