Skip to main content
Skip to footer
Home
Interview Questions
Machine Learning Basics
Deep Learning
Supervised Learning
Unsupervised Learning
Natural Language Processing
Statistics
Data Preparation
Technical Quizzes
Jobs
Home
Interview Questions
Machine Learning Basics
Deep Learning
Supervised Learning
Unsupervised Learning
Natural Language Processing
Statistics
Data Preparation
Technical Quizzes
Jobs
Login
Sign Up
Explore Questions by Topics
Computer Vision
(1)
Generative AI
(2)
Machine Learning Basics
(18)
–
Deep Learning
(52)
DL Basics
(16)
–
DL Architectures
(17)
Feedforward Network / MLP
(2)
Sequence models
(6)
Transformers
(9)
DL Training and Optimization
(17)
–
Natural Language Processing
(27)
NLP Data Preparation
(18)
–
Supervised Learning
(115)
–
Regression
(41)
Linear Regression
(26)
Generalized Linear Models
(9)
Regularization
(6)
–
Classification
(70)
Logistic Regression
(10)
Support Vector Machine
(9)
Ensemble Learning
(24)
Other Classification Models
(9)
Classification Evaluations
(9)
–
Unsupervised Learning
(55)
–
Clustering
(37)
Distance Measures
(9)
K-Means Clustering
(9)
Hierarchical Clustering
(3)
Gaussian Mixture Models
(5)
Clustering Evaluations
(6)
Dimensionality Reduction
(9)
Statistics
(34)
–
Data Preparation
(35)
Feature Engineering
(30)
Sampling Techniques
(5)
Deep Learning
Q.
What is Parameter Efficient Fine-Tuning (PEFT)?
Q.
What is a Vector Database and How is it used for RAG?
Q.
What is Knowledge Distillation?
Q.
Explain 𝐑𝐎𝐔𝐆𝐄 𝐚𝐧𝐝 𝐢𝐭s 𝐢𝐦𝐩𝐨𝐫𝐭𝐚𝐧𝐭 𝐢𝐧 𝐍𝐋𝐏
Q.
What is Instruction Fine-Tuning
Q.
What is Convolution?
Q.
Explain Perplexity
Q.
What is Precision@K?
Q.
What is Supervised Fine-Tuning?
Q.
Making Transformers Work: Scale, Access, Deployment and Ethics
Q.
Top 20 Deep Learning Interview Questions with detailed Answers (All free)
Q.
What is Deep Learning? Discuss the key characteristics, working and applications of Deep Learning
Q.
What are the advantages and disadvantages of Deep Learning?
Q.
How does Deep Learning methods compare with traditional Machine Learning methods?
Q.
Explain the basic architecture of a Neural Network, model training and key hyper-parameters
Q.
What is an activation function? What are the different types of activation functions? Discuss their pros and cons
Q.
What is Backpropagation?
Q.
What is a Perceptron? What is the role of bias in a perceptron (or neuron)?
Q.
What is a Multilayer Perceptron (MLP) or a Feedforward Neural Network (FNN)?
Q.
What are Sequence Models? Discuss the key Sequence modeling algorithms and their real world applications
Q.
What are the key hyper-parameters of a neural network model?
Q.
Sequence Models Compared: RNNs, LSTMs, GRUs, and Transformers
Q.
What is Rectified Linear Unit (ReLU) activation function? Discuss its advantages and disadvantages
Q.
What do you mean by pretraining, finetuning and transfer learning?
Q.
What is the vanishing and exploding gradient problem, and how are they typically addressed?
Q.
What do you mean by Sequence data? Discuss the different types
Q.
What are Transformers? Discuss the evolution, advantages and major breakthroughs in transformer models
Q.
Understanding the architecture of Recurrent Neural Networks (RNN)
Q.
What are the advantages and disadvantages of a Recurrent Neural Network (RNN)?
Q.
Explain the Transformer Architecture (with Examples and Videos)
Q.
What is Long-Short Term Memory (LSTM)?
Q.
What are the primary advantages of transformer models?
Q.
What are the limitations of transformer models?
Q.
Explain Self-Attention, and Masked Self-Attention as used in Transformers
Q.
Multi-Head Attention: Why It Outperforms Single-Head Models
Q.
What is the “dead ReLU” problem and, why is it an issue in Neural Network training?
Q.
Explain the need for Positional Encoding in Transformer models
Q.
Cross-Attention vs Self-Attention Explained
Q.
Why is Zero-centered output preferred for an activation function?
Q.
What is an activation function, and what are some of the most common choices for activation functions?
Q.
What do you mean by saturation in neural network training? Discuss the problems associated with saturation
Q.
What are some strategies to address Overfitting in Neural Networks?
Q.
What is Dropout?
Q.
What is the difference between Deep and Shallow networks?
Q.
Describe briefly the training process of a Neural Network model
Q.
What is Sigmoid (logistic) activation function?
Q.
Discuss TanH activation function
Q.
What are some options for making Backpropagation more efficient?
Q.
What is the difference between a Batch and an Epoch?
Q.
Discuss Softmax activation function
Q.
What are some guidelines for choosing activation functions?
Q.
How are Regression and Classification performed using multilayer perceptrons (MLP)?
Partner Ad
Explore Questions by Topics
Computer Vision
(1)
Generative AI
(2)
Machine Learning Basics
(18)
–
Deep Learning
(52)
DL Basics
(16)
–
DL Architectures
(17)
Feedforward Network / MLP
(2)
Sequence models
(6)
Transformers
(9)
DL Training and Optimization
(17)
–
Natural Language Processing
(27)
NLP Data Preparation
(18)
–
Supervised Learning
(115)
–
Regression
(41)
Linear Regression
(26)
Generalized Linear Models
(9)
Regularization
(6)
–
Classification
(70)
Logistic Regression
(10)
Support Vector Machine
(9)
Ensemble Learning
(24)
Other Classification Models
(9)
Classification Evaluations
(9)
–
Unsupervised Learning
(55)
–
Clustering
(37)
Distance Measures
(9)
K-Means Clustering
(9)
Hierarchical Clustering
(3)
Gaussian Mixture Models
(5)
Clustering Evaluations
(6)
Dimensionality Reduction
(9)
Statistics
(34)
–
Data Preparation
(35)
Feature Engineering
(30)
Sampling Techniques
(5)
Search
Join us on:
Machine Learning Interview Preparation Group
@OfficialAIML
Find out all the ways that you can
Contribute
Other Questions in Deep Learning
What are options to calibrate probabilities produced from the output of a classifier that does not produce natural probabilities?
What are the subtypes of Cross Validation?
What is Specificity?
Explain the concept and working of the Random Forest model
How does a learning curve give insight into whether the model is under- or over-fitting?
What is the difference between Discriminative and Generative models?