Python / Python Deep Learning and Neural Networks Interview Questions

What is knowledge distillation and how does it compress large neural networks into smaller ones?

Knowledge distillation (Hinton et al., 2015) trains a small student network to mimic the output distribution of a large, accurate teacher network. Instead of training only on hard labels (the correct class as a one-hot vector), the student is also trained to match the teacher's soft probabilities — the full output distribution including small probabilities assigned to incorrect classes.

The soft probabilities carry richer information than hard labels: if the teacher assigns 0.7 to 'cat' and 0.25 to 'dog', this communicates that the image looks somewhat cat-like but also dog-like — a nuanced signal the student can learn from. A temperature parameter T sharpens or softens this distribution: p_i = exp(z_i/T) / Σ exp(z_j/T). Higher T produces a softer, more uniform distribution that exposes the teacher's confidence relationships across all classes, giving the student a richer gradient signal. The distillation loss combines the cross-entropy with hard labels and the KL divergence with the teacher's soft targets.

import torch
import torch.nn as nn
import torch.nn.functional as F

teacher = BigModel().eval()      # pretrained, frozen
student = SmallModel()           # to be trained

T           = 3.0   # temperature â soften the distributions
alpha       = 0.7   # weight for distillation vs hard-label loss
ce_loss     = nn.CrossEntropyLoss()
kl_div_loss = nn.KLDivLoss(reduction='batchmean')

optimizer = torch.optim.AdamW(student.parameters(), lr=1e-3)

for X, y_hard in loader:
    # Teacher forward (no grad)
    with torch.no_grad():
        teacher_logits = teacher(X)

    # Student forward
    student_logits = student(X)

    # Hard-label cross-entropy
    loss_hard = ce_loss(student_logits, y_hard)

    # Soft-target KL divergence (temperature-scaled)
    student_soft = F.log_softmax(student_logits / T, dim=1)
    teacher_soft = F.softmax(teacher_logits / T, dim=1)
    loss_kl = kl_div_loss(student_soft, teacher_soft) * (T ** 2)
    # T^2 scaling: compensates for the T-scaled gradients

    loss = alpha * loss_kl + (1 - alpha) * loss_hard
    optimizer.zero_grad(); loss.backward(); optimizer.step()

Take quiz

Why are 'soft probabilities' from a teacher network more informative than one-hot hard labels for training a student?Soft probabilities contain more data per sample than hard labels

✗ Try again.

Soft probabilities encode the teacher's uncertainty and the similarity structure between classes — e.g. a small probability on 'dog' when the true class is 'cat' reveals that the input has dog-like features, providing richer gradient signal than a one-hot label that treats all wrong classes identically

✓ Correct! Well done.

Hard labels cause the cross-entropy loss to become non-convex

✗ Try again.

Soft probabilities allow the student network to have more parameters than the teacher

✗ Try again.

Why is the KL divergence term multiplied by T² in the distillation loss?T² normalises the loss to have the same scale as cross-entropy

✗ Try again.

Using temperature T in softmax divides the logits by T, which reduces gradient magnitudes by T² via the chain rule — multiplying by T² restores the gradient to the original scale, ensuring the distillation term has appropriate influence relative to the hard-label term

✓ Correct! Well done.

T² prevents the soft targets from summing to more than 1

✗ Try again.

T² is a convention from the original paper with no mathematical justification

✗ Try again.

More Related questions...

What is a neural network and how does forward propagation work mathematically? Explain backpropagation mathematically. How does the chain rule enable computing gradients through many layers? What are the most common activation functions and why did ReLU replace sigmoid/tanh as the default? What are vanishing and exploding gradients, and what techniques are used to address them? Why does weight initialization matter in neural networks, and what is the difference between Xavier and He initialization? How does Batch Normalization work mathematically and why does it stabilize training? Compare SGD, SGD with momentum, RMSProp, and Adam optimizers. When do you choose each? How does Dropout work mathematically, and why does it act as regularization? Explain how convolutional layers work and why they are well-suited to image data. How do RNNs work and why did LSTMs solve the long-range dependency problem? What is the self-attention mechanism in Transformers and why did it replace RNNs for sequence modeling? What loss functions does PyTorch provide for classification and regression, and which to use when? What is transfer learning and how do you fine-tune a pretrained model in PyTorch? How does PyTorch's Dataset and DataLoader pipeline work, and what are the key performance considerations? Why is learning rate scheduling important and what are the most common strategies? What are the most effective regularization strategies for deep learning and how do they differ from classical ML regularization? What are embedding layers in deep learning and how are they different from one-hot encoding? How do you save and load PyTorch models correctly, and what is included in a proper checkpoint? What is mixed precision training and how does it speed up deep learning with torch.cuda.amp? What is the difference between model.eval(), torch.no_grad(), and torch.inference_mode()? When do you use each? How do you use GPUs in PyTorch and what are the key patterns for writing device-agnostic code? What are the differences between Batch Norm, Layer Norm, Group Norm, and Instance Norm? What is an autoencoder and what can a well-trained latent space be used for? How do you diagnose a neural network that is not training correctly from its loss curves? What is the mathematical setup of a Generative Adversarial Network (GAN) and what training challenges do they have? What is torch.compile and how does it speed up PyTorch model execution? Why do Transformers need positional encodings and how does sinusoidal encoding work? What are the most impactful hyperparameters to tune in deep learning and what is the recommended search order? What is an encoder-decoder architecture and how is it used for sequence-to-sequence tasks? What is model quantization in deep learning and how does PyTorch support it? What does a production-quality PyTorch training loop look like, incorporating all best practices? How does batch size affect deep learning training mathematically and practically? How do you choose the right layer type (Linear, Conv, Attention) for a given input modality? What evaluation metrics are most commonly used in deep learning tasks and how do you implement them in PyTorch? How do you export a PyTorch model for production deployment using TorchScript or ONNX? What is knowledge distillation and how does it compress large neural networks into smaller ones? What is self-supervised learning and how do contrastive methods like SimCLR learn representations? How would you implement and train a simple feedforward neural network in PyTorch from scratch, without using nn.Sequential?

Show more question and Answers...

Python Modern Generative AI and Agents Interview Questions

	Interviews Questions Java Spring Hibernate DevOps Testing API BigData Web Erlang AI Database Integration Cloud Python Scala Tools Golang SAP	About Javapedia.net Javapedia.net is for Java and J2EE developers, technologist and college students who prepare of interview. Also this site includes many practical examples. This site is developed using J2EE technologies by Steve Antony, a senior Developer/lead at one of the logistics based company. Follow Javapedia updates
	contact: javatutorials2016[at]gmail[dot]com
Kindly consider donating for maintaining this website. Thanks.
	Copyright © 2026, javapedia.net, all rights reserved. Privacy Policy · Terms of Service.

Python / Python Deep Learning and Neural Networks Interview Questions

What is knowledge distillation and how does it compress large neural networks into smaller ones?

Comments & Discussions

Recently added questions