Junior interview questionAsked at C3 AI · interview write-up
Which of these does not reliably fix vanishing gradients: skip connections, ReLU, a higher learning rate or batch normalization? Why?
Model answer
A higher learning rate. It scales every update equally, so early layers stay starved while late ones turn unstable. The others attack the cause: skip connections give gradients a direct path, ReLU has slope one when active instead of saturating, and batch normalization keeps activations in a healthy range.
Practise the rest
35 Training questions, 492 in all, each with a model answer. Free.
More from C3 AI interview questions.
More Training interview questions
- Implement masked cross-entropy in NumPy that stays numerically stable, with label smoothing and a temperature.
- Build a pipeline that finds math documents in web crawls and scores their quality.
- Explain KL divergence for language models: which direction is which, what happens when supports don't match, and how it's used as a regulariser.
- When would you use mean squared error versus cross-entropy? And what is LoRA?
- Explain Adam and its bias correction, and why AdamW decouples weight decay.
- Explain policy types in RL and modern policy-gradient methods such as TRPO, PPO and GAE, then compare linear attention and grouped-query attention.