Loading…
Cross-Entropy Loss and Gradient is a medium coding interview question covering math, deep learning, machine learning — the kind asked at FAANG (Facebook/Meta, Apple, Amazon, Netflix, Google) and AI-first companies like Anthropic, OpenAI, and Nvidia.
Given raw logits and a target class index, compute the softmax cross-entropy loss and its gradient with respect to the logits, with numerical stability. This is the loss function behind essentially every classifier and language model.
Solution walkthrough on Pro
Upgrade to Pro to unlock the guided hints, the step-by-step walkthrough, solutions in Python, C++, Java, and Go, and complexity analysis.
What's inside this guide
Fully unlocked, no account needed — solutions, walkthroughs and follow-up answers included.
Or start the Study Plan — a week-by-week order for your loop, and week 1 is entirely free.
A full interview loop is more than one round. These are the others, each with what is on the site for it.