Quick Revision

GK One-Line Question & Answer

15541+ short questions with short answers, covering every category and sub-category on the site — no long articles to scroll through. Good for a fast recap before an exam, or a few minutes of daily practice.

Looking for exam process/strategy questions instead? Try the Exam Preparation FAQ →

Computer Fundamentals → Introduction to Computer 36

Learning rate in neural networks?
Controls step size in weight updates during training
click to copy
Dropout regularization randomly?
Deactivates random neurons during training to prevent overfitting
click to copy
Batch normalization normalizes?
Activations within each mini-batch, stabilizing training
click to copy
Transfer learning uses?
Pre-trained model weights as starting point for new task
click to copy
Attention mechanism in transformers computes?
Weighted sum of values based on query-key similarity
click to copy
Self-attention in transformers?
Computes attention within the same sequence — every token attends to all others
click to copy
GPT models are?
Auto-regressive — generate text left to right using decoder-only transformer
click to copy
Which evaluation metric is used for classification with imbalanced classes?
F1 score (harmonic mean of precision and recall)
click to copy
Precision in classification is?
TP/(TP+FP) — of all predicted positive, how many are actually positive
click to copy
Recall (Sensitivity) is?
TP/(TP+FN) — of all actual positives, how many were correctly identified
click to copy
ROC curve plots?
True Positive Rate vs False Positive Rate at various thresholds
click to copy
AUC (Area Under ROC Curve) of 1.0 means?
Perfect classifier
click to copy
K-fold cross-validation partitions data into?
K folds — train on K-1, validate on 1, repeat K times
click to copy
Which ML algorithm is based on Bayes' theorem?
Naïve Bayes classifier
click to copy
Support Vector Machine (SVM) finds?
Maximum margin hyperplane separating classes
click to copy
Random forest is an ensemble of?
Decision trees trained on random subsets with feature randomness
click to copy
Boosting ensemble method?
Trains models sequentially, each correcting previous model's errors
click to copy
XGBoost is based on?
Gradient boosted decision trees with regularization
click to copy
PCA (Principal Component Analysis) is used for?
Dimensionality reduction by finding principal variance directions
click to copy
t-SNE is used for?
High-dimensional data visualization in 2D/3D
click to copy
DBSCAN clustering algorithm?
Discovers clusters of arbitrary shape based on density
click to copy
Hierarchical clustering produces?
Dendrogram — tree showing cluster merges at different distances
click to copy
Autoencoder is used for?
Unsupervised feature learning, dimensionality reduction, anomaly detection
click to copy
GAN (Generative Adversarial Network) consists of?
Generator (creates fake data) and Discriminator (detects fakes) competing
click to copy
ACID vs BASE in databases: BASE means?
Basically Available, Soft-state, Eventually consistent
click to copy
CROSS JOIN produces?
Cartesian product — all combinations of rows from both tables
click to copy
SELF JOIN joins a table?
To itself
click to copy
Which SQL command changes table structure?
ALTER TABLE
click to copy
Database view vs materialized view: materialized view?
Stores result physically — faster queries but needs periodic refresh
click to copy
OLAP vs OLTP: OLAP is used for?
Analytical queries on large datasets (data warehousing)
click to copy
Star schema in data warehouse has?
Central fact table surrounded by dimension tables
click to copy
ETL stands for?
Extract, Transform, Load
click to copy
Which database is used for time-series data?
InfluxDB/TimescaleDB
click to copy
Graph databases like Neo4j use which query language?
Cypher
click to copy
Elasticsearch is primarily used for?
Full-text search and log analytics
click to copy
TF-IDF measures?
Term relevance — frequency in document vs rarity across documents
click to copy

Computer Fundamentals → Memory Units 2

BERT (Bidirectional Encoder Representations from Transformers) is pre-trained using?
Masked Language Modeling (MLM) and Next Sentence Prediction (NSP)
click to copy
Which SQL join returns all from left table even with no right match?
LEFT JOIN
click to copy

Computer Fundamentals → Operating System Basics 1

Kernel trick in SVM allows?
Non-linear classification by mapping data to higher-dimensional space
click to copy

Computer Fundamentals → Internet Basics 1

Inverted index is used by search engines to?
Map words to documents containing them (enables fast text search)
click to copy