InterviewStack.io LogoInterviewStack.io

Training Deep Learning Models Questions

Understand the training process: feeding data through the network, computing loss, backpropagating, updating weights, and iterating until convergence. Know about batching, epochs, validation splits, and early stopping. Understand overfitting, underfitting, and the bias-variance trade-off. Know techniques to address overfitting: regularization, dropout, data augmentation, batch normalization.

HardTechnical
86 practiced
Discuss the trade-offs between small and very large batch sizes. Explain how batch size affects optimization dynamics, gradient noise scale, generalization gap at large batch sizes, and how scaling rules (e.g., linear scaling of learning rate) attempt to compensate. Provide practical recommendations for batch size selection under hardware constraints.
EasyTechnical
79 practiced
Explain clearly the difference between epoch, iteration, and batch in deep learning training. Use an example dataset of 12,000 samples and batch size 128 to compute the number of iterations per epoch and total iterations after 10 epochs. Discuss how these terms affect logging, learning rate schedules, and checkpoint frequency.
HardTechnical
89 practiced
Implement a PyTorch Dataset.__getitem__ that performs on-the-fly augmentation, caches preprocessed images to disk to speed up repeated epochs, and uses deterministic per-worker random seeds. Show use of worker_init_fn to seed numpy and random per worker and describe cache invalidation strategy when augmentation pipeline changes.
HardTechnical
73 practiced
Explain in detail how backpropagation computes gradients for a 2D convolutional layer and for batch normalization. Describe tensor shapes involved in computing gradients wrt inputs, filters, and BN parameters, and mention common implementation optimizations (im2col, GEMM) used by libraries like cuDNN.
HardTechnical
69 practiced
Derive how Batch Normalization changes gradient flow through a layer and discuss the intuition behind reducing internal covariate shift. Include an explanation of how normalization affects the gradient magnitude and direction and discuss issues such as interaction with dropout, small batch sizes, and moving averages of statistics.

Unlock Full Question Bank

Get access to hundreds of Training Deep Learning Models interview questions and detailed answers.

Sign in to Continue

Join thousands of developers preparing for their dream job.