AI & Machine Learning Interview Questions

Question 1

What is the difference between AI, Machine Learning, and Deep Learning?

Accepted Answer

AI is the broad field of intelligent machines; ML is a subset using data to learn patterns; DL is a subset of ML using neural networks. AI: any technique enabling machines to mimic human intelligence. ML: algorithms that learn from data without explicit programming (supervised, unsupervised, reinforcement). DL: multi-layer neural networks that learn hierarchical representations. Relationship: AI ⊃ ML ⊃ DL. Examples: AI (Siri), ML (spam filter), DL (image recognition, GPT).

Question 2

What is supervised vs unsupervised learning?

Accepted Answer

Supervised learning trains on labeled data (input→output pairs); unsupervised learning finds patterns in unlabeled data. Supervised: classification (spam/not spam), regression (predict price). Algorithms: Linear Regression, Decision Trees, SVM, Neural Networks. Unsupervised: clustering (customer segments), dimensionality reduction (PCA), association rules. Algorithms: K-Means, DBSCAN, Hierarchical Clustering, t-SNE. Semi-supervised: mix of labeled and unlabeled data. Self-supervised: creates labels from data itself (BERT, GPT).

Question 3

What is overfitting and how do you prevent it?

Accepted Answer

Overfitting is when a model learns training noise instead of patterns, performing well on training but poorly on new data. Signs: high training accuracy, low test accuracy. Prevention: (1) More training data. (2) Regularization (L1/L2). (3) Cross-validation. (4) Dropout (neural networks). (5) Early stopping. (6) Simpler model. (7) Data augmentation. (8) Ensemble methods. (9) Feature selection. Underfitting: model too simple, poor on both train and test. Balance bias-variance tradeoff.

Question 4

What are the common evaluation metrics for ML models?

Accepted Answer

Classification: accuracy, precision, recall, F1-score, AUC-ROC. Regression: MSE, RMSE, MAE, R-squared. Classification: Accuracy (overall correctness), Precision (true positives / predicted positives), Recall (true positives / actual positives), F1 (harmonic mean of precision/recall), AUC-ROC (discrimination ability). Regression: MSE (mean squared error), RMSE (root MSE, same units), MAE (mean absolute error), R² (variance explained). Choose based on business need: medical diagnosis needs high recall; spam filter needs high precision.

Question 5

What is a neural network?

Accepted Answer

A neural network is layers of interconnected nodes (neurons) that learn to transform inputs into outputs through weighted connections. Architecture: input layer, hidden layers, output layer. Each neuron: weighted sum of inputs → activation function → output. Training: forward pass (predict), loss calculation, backward pass (gradients via backpropagation), weight update (optimizer like SGD, Adam). Activation functions: ReLU (hidden layers), Sigmoid (binary output), Softmax (multi-class). Deep networks: many hidden layers enable learning complex hierarchical features.

Question 6

What is the bias-variance tradeoff?

Accepted Answer

Bias is error from wrong assumptions (underfitting); variance is error from sensitivity to training data noise (overfitting). High bias: model too simple, misses patterns (linear model for nonlinear data). High variance: model too complex, memorizes noise. Total error = bias² + variance + irreducible error. Balance: (1) Model complexity vs data size. (2) Regularization reduces variance. (3) Ensemble methods (bagging reduces variance, boosting reduces bias). (4) Cross-validation to estimate both. Goal: minimize total error, not just one component.

Question 7

Explain the difference between CNN and RNN.

Accepted Answer

CNNs process spatial data (images) using convolutional filters; RNNs process sequential data (text, time series) with memory cells. CNN: convolutional layers extract spatial features (edges → shapes → objects), pooling layers reduce dimensions. Used for: image classification, object detection, segmentation. RNN: hidden state carries information across time steps. Variants: LSTM (long-term memory), GRU (simpler). Used for: text, speech, time series. Modern: Transformers largely replaced RNNs for NLP (attention mechanism avoids sequential bottleneck). Vision Transformers (ViT) challenging CNNs.

Question 8

What is transfer learning?

Accepted Answer

Transfer learning uses a pre-trained model on a large dataset as a starting point, then fine-tunes it for a specific task with less data. Process: (1) Take model pre-trained on large dataset (ImageNet, Wikipedia). (2) Freeze early layers (general features). (3) Replace final layers for your task. (4) Fine-tune on your smaller dataset. Benefits: less data needed, faster training, better performance. Examples: BERT/GPT fine-tuned for classification, ResNet fine-tuned for medical imaging. Foundation models (GPT-4, DALL-E) are the ultimate transfer learning — trained once, used for many tasks.

Question 9

What is gradient descent and its variants?

Accepted Answer

Gradient descent optimizes model parameters by iteratively moving in the direction that reduces the loss function. Variants: (1) Batch GD: uses entire dataset per step (stable but slow). (2) Stochastic GD (SGD): one sample per step (noisy but fast). (3) Mini-batch GD: compromise (most common, batch size 32-256). Optimizers: Momentum (accelerates convergence), RMSprop (adaptive learning rate), Adam (combines momentum + RMSprop, most popular). Learning rate scheduling: warmup, cosine annealing, step decay. Gradient clipping prevents exploding gradients.

Question 10

What are Transformers and how do they work?

Accepted Answer

Transformers use self-attention mechanisms to process sequences in parallel, powering models like GPT, BERT, and Vision Transformers. Architecture: encoder-decoder with multi-head self-attention and feed-forward layers. Self-attention: each token attends to all other tokens (computes relevance scores). Positional encoding adds sequence order. Benefits over RNNs: parallel processing, long-range dependencies, scalable. BERT: encoder-only (understanding). GPT: decoder-only (generation). T5: encoder-decoder (both). Scale: GPT-4 has trillions of parameters. Attention complexity: O(n²) — ongoing research to reduce (Flash Attention, sparse attention).

AI & Machine Learning Course 2026 - From Basics to Advanced

What You'll Learn

Career Opportunities

Course Completion Certificate

Course Modules Overview

Introduction to AI and Machine Learning

Python for Data Science

Supervised Learning

Unsupervised Learning

Deep Learning and Neural Networks

Advanced Deep Learning

MLOps & Model Management

Big Data & Distributed ML

AI Research & Innovation

Computer Vision & Image Processing

Natural Language Processing

MLOps and Production Deployment

Course Curriculum

Introduction to AI and Machine Learning

Python for Data Science

Supervised Learning

Unsupervised Learning

Deep Learning and Neural Networks

Advanced Deep Learning

MLOps & Model Management

Big Data & Distributed ML

AI Research & Innovation

Computer Vision & Image Processing

Natural Language Processing

MLOps and Production Deployment

Your Learning Path

Beginner

Intermediate

Advanced

Tools & Technologies

Python 3.11+

TensorFlow 2.x

PyTorch

Scikit-learn

Jupyter Notebooks

Google Colab

Ready to Start Learning?

Related Free Courses

Python Django Course

Cloud & DevOps Course

SQL Course

JavaScript Course