Your question is Avoiding Deep Learning Pitfalls. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
What are some common pitfalls in deep learning, and how can they be avoided?
Discuss practical failure modes across data preparation, model design, optimization, evaluation, and deployment. Explain how you would detect each problem, choose an appropriate mitigation, and verify that the mitigation improves generalization rather than only training performance.