Artificial Intelligence & Machine Learning MCQ
Test your AI & Machine Learning knowledge with 100 multiple choice questions covering fundamentals to advanced concepts, with instant feedback and explanations.
What is machine learning?
2What is the difference between supervised and unsupervised learning?
3What is overfitting in machine learning?
4What is a neural network?
5What is gradient descent?
6What is the purpose of a training, validation, and test set?
7What is a decision tree?
8What is k-means clustering?
9What is linear regression?
10What is logistic regression?
11What is a Random Forest?
12What is the bias-variance tradeoff?
13What is cross-validation?
14What is precision and recall?
15What is the F1 score?
16What is feature engineering?
17What is a support vector machine (SVM)?
18What is deep learning?
19What is a convolutional neural network (CNN)?
20What is a recurrent neural network (RNN)?
21What is transfer learning?
22What is natural language processing (NLP)?
23What is reinforcement learning?
24What is the purpose of regularization in ML?
25What is a confusion matrix?
26What is dimensionality reduction?
27What is the curse of dimensionality?
28What is a generative model vs a discriminative model?
29What is data augmentation?
30What is the ROC curve and AUC?
31What is a hyperparameter?
32What is batch normalization?
33What is dropout in neural networks?
34What is the attention mechanism in deep learning?
35What is GPT?
36What is a loss function?
37What is an activation function?
38What is the difference between classification and regression?
39What is the softmax function?
40What is a knowledge graph?
What is the transformer architecture and why did it revolutionize AI?
2What is BERT and how does it differ from GPT?
3What is fine-tuning a pre-trained model?
4What is a GAN (Generative Adversarial Network)?
5What is a VAE (Variational Autoencoder)?
6What is word2vec?
7What is the vanishing gradient problem?
8What is LSTM and how does it address the vanishing gradient problem?
9What is object detection and how does it differ from image classification?
10What is the purpose of residual connections (skip connections) in deep networks?
11What is RLHF (Reinforcement Learning from Human Feedback)?
12What is prompt engineering?
13What is RAG (Retrieval-Augmented Generation)?
14What is the difference between precision-recall and ROC curves?
15What is gradient clipping?
16What is knowledge distillation?
17What is neural architecture search (NAS)?
18What is a recommendation system?
19What is concept drift in machine learning?
20What is federated learning?
21What is a vector database and why is it used in AI applications?
22What is LoRA (Low-Rank Adaptation)?
23What is the difference between model accuracy and fairness in ML?
24What is mean squared error (MSE) vs mean absolute error (MAE)?
25What is model explainability (XAI)?
26When should you choose a decision tree over logistic regression for a classification task?
27What is the elbow method used for in clustering?
28What is stratified sampling and why is it used when splitting a dataset?
29Why is one-hot encoding commonly used for categorical features in machine learning?
30What is the main practical tradeoff when increasing the depth of a decision tree?
31In scikit-learn-style workflows, what is the purpose of a Pipeline object?
32What is early stopping during neural network training?
33What is the difference between bagging and boosting as ensemble techniques?
34Why might you use the Adam optimizer instead of plain stochastic gradient descent (SGD) when training a neural network?
35What is data leakage in a machine learning workflow?
36What is the purpose of the learning rate schedule (e.g., step decay or cosine annealing) during training?
37What is tokenization in the context of NLP and language models?
38What is the purpose of a learning curve (training size vs. error) when diagnosing a model?
39Why is min-max scaling or standardization often applied before training algorithms like k-NN or SVM?
40What is the practical difference between using grid search and random search for hyperparameter tuning?
What is self-supervised learning and how is it used in modern AI?
2What is the scaling law in large language models?
3What is the attention mechanism complexity and how does sparse attention address it?
4What is the mixture of experts (MoE) architecture?
5What is mechanistic interpretability in LLMs?
6What is the difference between in-context learning and fine-tuning in LLMs?
7What is Constitutional AI (CAI) and how does it improve alignment?
8What is a neural ordinary differential equation (Neural ODE)?
9What is the difference between model parallelism and data parallelism in distributed training?
10What is activation engineering/steering in LLMs?
11What is the alignment problem in AI?
12What is multi-modal learning in AI?
13What is emergent ability in large language models?
14What is the temperature parameter in LLM sampling?
15What is speculative decoding in LLMs?
16What is Constitutional AI and RLAIF vs RLHF?
17What is the difference between zero-shot, one-shot, and few-shot prompting?
18What is catastrophic forgetting in neural networks?
19Mathematically, why does L2 regularization (Ridge) tend to shrink weights smoothly toward zero rather than setting them exactly to zero, unlike L1 (Lasso)?
20In the bias-variance decomposition of expected prediction error, what does the irreducible error term represent, and why can no model eliminate it?