AI/ML Interview Questions with Answers
General AI Questions
Q1: What is Artificial Intelligence (AI)?
A1: AI is the simulation of human intelligence processes by machines, especially computer systems.
Q2: What are the types of AI?
A2: 1. Reactive Machines
2. Limited Memory
3. Theory of Mind
4. Self-aware AI
Q3: Difference between AI, Machine Learning, and Deep Learning?
A3: AI is the broader concept of machines being able to carry out tasks in a smart way. ML is a
subset of AI that involves training algorithms to learn from data. Deep Learning is a further subset of
ML using neural networks.
Q4: What are some real-world applications of AI?
A4: Examples include virtual assistants, recommendation systems, autonomous vehicles, and
medical diagnosis.
Q5: What is the Turing Test?
A5: A test to determine if a machine can exhibit intelligent behavior equivalent to, or
indistinguishable from, that of a human.
Basic Machine Learning Questions
Q1: What is Machine Learning (ML)?
A1: ML is a subset of AI that allows systems to learn and improve from experience without being
explicitly programmed.
Q2: What are the types of ML?
A2: 1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning
Q3: Difference between Supervised and Unsupervised Learning?
A3: Supervised Learning uses labeled data; Unsupervised Learning finds patterns in unlabeled data.
Q4: What is overfitting and underfitting?
A4: Overfitting is when the model performs well on training data but poorly on test data. Underfitting
is when the model performs poorly on both.
Q5: What is a dataset, feature, and label?
A5: Dataset: Collection of data. Feature: Input variable. Label: Output variable or target.
Q6: What is a model in ML?
A6: An ML model is a mathematical representation trained on data to make predictions or decisions.
Q7: How do you evaluate an ML model?
A7: Using metrics like Accuracy, Precision, Recall, and F1 Score.
ML Techniques & Algorithms
Q1: Name a few common ML algorithms.
A1: Linear Regression, Logistic Regression, Decision Trees, KNN, SVM, Random Forest.
Q2: What is regression vs classification?
A2: Regression predicts continuous values; classification predicts discrete labels.
Q3: What is clustering?
A3: A method of unsupervised learning used to group similar data points together.
Q4: What is the KNN algorithm?
A4: K-Nearest Neighbors is a simple algorithm that stores all instances and classifies new data
based on majority vote of its neighbors.
Q5: What is a decision tree?
A5: A flowchart-like structure where each internal node represents a feature test, each branch a
result, and each leaf a class label.
Data Preprocessing & Feature Engineering
Q1: What is data cleaning or preprocessing?
A1: It involves removing or correcting data that is incorrect, incomplete, or irrelevant.
Q2: What is imputation in ML?
A2: Filling in missing values using strategies like mean, median, or mode.
Q3: What is encoding in ML?
A3: Transforming categorical data into numerical format. E.g., One-Hot Encoding, Label Encoding.
Q4: What is normalization vs standardization?
A4: Normalization rescales data to [0,1]; standardization rescales data to have mean 0 and variance
1.
Q5: Why do we split data into training and testing sets?
A5: To evaluate the model's performance on unseen data.
AI/ML Tools & Libraries
Q1: Which programming language is most commonly used in ML?
A1: Python.
Q2: Name some ML libraries in Python.
A2: Scikit-learn, TensorFlow, Keras, PyTorch, pandas, NumPy.
Q3: What is TensorFlow used for?
A3: An open-source library for numerical computation and machine learning.
Q4: What is the use of pandas and NumPy?
A4: pandas is used for data manipulation; NumPy for numerical operations on arrays.
Simple Conceptual Questions
Q1: What is a neural network?
A1: A neural network is a series of algorithms that mimic the operations of a human brain to
recognize relationships in data.
Q2: What is an epoch in training?
A2: One complete pass through the entire training dataset.
Q3: What is gradient descent?
A3: An optimization algorithm used to minimize the loss function by updating model parameters.
Q4: What is bias and variance in ML?
A4: Bias is error due to overly simplistic assumptions; variance is error due to too much complexity.
Q5: Why is AI important for the future?
A5: AI can automate tasks, improve decision-making, and enable new technologies across
industries.
