Dataford
Top 50
Topic roadmap
Updated weekly · Last refresh Sep 13

Top 50 backpropagation Interview Questions

The most frequently asked backpropagation questions across all roles and companies, ranked by real interview frequency. Updated daily.

50questions
~9htotal time
42companies covered
Track your progressSign up free to work through all 50 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 11 questions · ~114 min
Masked Attention with PyTorchHard
Practice

Compute scaled dot-product attention over batched, multi-head sequences with boolean masks and fully masked query handling.

backpropagationArraysAlgorithmsAdobe
Neural Network Forward Pass in NumPyHard
Practice

Compute hidden-layer ReLU activations and stable softmax outputs for a batched NumPy neural network.

backpropagationArraysbroadcastingOpenAI
Implement Binary Focal Loss GradientsHard
Practice

Implement numerically stable binary focal loss and its backward pass from logits, including reduction handling.

backpropagationloss functionsnumpyWaymo
Neural Network ImplementationHard
Practice

Implement a one-hidden-layer neural network from scratch using sigmoid activation and batch backpropagation.

backpropagationRecursionCodingFactored
Backpropagation ImplementationHard
Practice

Compute gradients for a two-layer neural network using vectorized backpropagation and softmax cross-entropy.

Neural NetworksbackpropagationGradient DescentOpenAI
Custom Loss Function in PyTorchMedium
Practice

Implement piecewise Huber loss with element-wise, mean, and sum reductions using Python-compatible tensor semantics.

backpropagationloss functionsArraysQuest Global
Focal Loss ImplementationHard
Practice

Compute mean binary focal loss from logits and labels using numerically stable log-probability calculations.

backpropagationArraysAlgorithmsAmazon Web Services
More Coding questions with a free account

Sign up to see every question

Create a free account to unlock this list and practice real interview questions.

Get my prep plan
2
Machine Learning39 questions · ~405 min
Backpropagation ExplanationHard
Recently asked

Explain backpropagation, chain-rule gradient flow, and parameter updates in a feed-forward neural network.

Neural NetworksbackpropagationDeep LearningAmazonAccenture
More Machine Learning questions with a free account
The finish line: interview-readyComplete all 50 questions to finish this plan.