Python / Python Deep Learning and Neural Networks Interview Questions

How do you choose the right layer type (Linear, Conv, Attention) for a given input modality?

Each layer type encodes different structural assumptions (inductive biases) about the data. Using a layer whose assumptions match the data's structure allows the model to learn faster and with less data than a generic alternative.

Layer Selection by Modality and Structure
Data type	Structure	Recommended layer	Reason
Tabular	No spatial/sequential structure	Linear (MLP)	Features are independent; no shared structure to exploit
Images	2D spatial locality + translation equivariance	Conv2d	Same pattern anywhere in image; fewer params than FC
Text/sequences	Long-range dependencies, variable length	Transformer (self-attention)	O(1) path length between any two positions
Short sequences / time series	Local temporal patterns	Conv1d or LSTM	Local: Conv1d; long-range: LSTM
Graphs	Irregular node connectivity	Graph Conv (GCN/GAT)	Aggregates neighbor information per node
Point clouds	Permutation invariant 3D	PointNet / sparse conv	Must handle unordered sets

import torch
import torch.nn as nn

# Tabular data: simple MLP
mlp = nn.Sequential(
    nn.Linear(30, 128), nn.ReLU(), nn.Dropout(0.2),
    nn.Linear(128, 64), nn.ReLU(),
    nn.Linear(64, 1)
)

# Image: CNN
cnn = nn.Sequential(
    nn.Conv2d(3, 32, 3, padding=1), nn.BatchNorm2d(32), nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(32, 64, 3, padding=1), nn.BatchNorm2d(64), nn.ReLU(),
    nn.AdaptiveAvgPool2d(1),   # global average pooling -> (B, 64, 1, 1)
    nn.Flatten(),
    nn.Linear(64, 10)
)

# Text: embedding + transformer encoder
encoder_layer = nn.TransformerEncoderLayer(
    d_model=256, nhead=4, dim_feedforward=512,
    dropout=0.1, batch_first=True
)
text_model = nn.Sequential(
    nn.Embedding(10000, 256),
    nn.TransformerEncoder(encoder_layer, num_layers=4)
)

# Time series: Conv1d (local patterns) or LSTM (sequential patterns)
ts_cnn = nn.Conv1d(in_channels=1, out_channels=32, kernel_size=5, padding=2)
ts_rnn = nn.LSTM(input_size=1, hidden_size=64, batch_first=True)

Take quiz

Why is Conv2d more parameter-efficient than a fully-connected layer for image data?Conv2d layers are always faster due to CUDA optimization

✗ Try again.

Conv2d shares the same filter weights across all spatial positions — a 3x3 filter has only 3x3xCxC_out parameters regardless of image size, while a fully-connected layer needs separate weights per input-output pixel pair, scaling as H×W×H'×W'×C×C_out

✓ Correct! Well done.

Conv2d can only process images of fixed resolution

✗ Try again.

Fully-connected layers cannot be applied to 2D data

✗ Try again.

When would you choose LSTM over a Transformer for sequence modelling?LSTM always outperforms Transformers for sequences

✗ Try again.

For very long sequences with limited compute or memory, or when processing streaming data token-by-token in production (LSTMs have O(1) inference cost per new token vs O(seq_len) for transformers); also when the training dataset is too small to learn the complex attention patterns

✓ Correct! Well done.

LSTM is required for sequences with more than 512 tokens

✗ Try again.

LSTM is used when the sequence contains numerical values; Transformer for text only

✗ 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

How do you choose the right layer type (Linear, Conv, Attention) for a given input modality?

Comments & Discussions

Recently added questions