Create a custom practice set
Pick category, difficulty, number of questions, and time limit. Start instantly with your own quiz.
Generate QuizGK Questions
Filter by category, type, and difficulty. Reading is open for everyone.
Which technique handles imbalanced datasets by adjusting class weights during training?
- Oversampling
- Undersampling
- Class Weighting
- All of these
Answer: All of these
Imbalance handling: oversampling (SMOTE) increases minority, undersampling reduces majority, class weighting adjusts loss function. Choice depends on data size and model type.
Which metric is most appropriate for evaluating regression models?
- Accuracy
- Precision
- RMSE
- F1 Score
Answer: RMSE
Regression metrics: RMSE (Root Mean Square Error) penalizes large errors, MAE for robustness, R² for variance explained. Choice depends on business impact of errors.
Which pattern enables stateless microservices to scale independently based on load?
- Stateless Design
- Horizontal Scaling
- Both A and B
- Neither
Answer: Both A and B
Stateless microservices store session data externally (Redis, database), enabling horizontal scaling by adding instances. Critical for elastic, resilient cloud applications.
Which service enables serverless data processing triggered by events?
- Lambda
- Cloud Functions
- Both A and B
- Neither
Answer: Both A and B
Serverless compute (AWS Lambda, GCP Cloud Functions) executes code in response to events: API calls, file uploads, messages. Auto-scaling, pay-per-execution pricing. Critical for event-driven architectures.
Which technology provides endpoint detection and response capabilities for advanced threats?
- EDR
- XDR
- Both A and B
- Neither
Answer: Both A and B
EDR focuses on endpoint telemetry and response; XDR extends to network, cloud, email for cross-domain threat detection. Critical for comprehensive threat protection.
Which practice ensures ML models are monitored for performance degradation in production?
- Drift Detection
- Metric Dashboards
- Alerting
- All of these
Answer: All of these
Production monitoring: drift detection for data/concept changes, dashboards for real-time metrics, alerting for anomalies. Critical for maintaining ML system reliability and business value.
Which technique enables LLMs to maintain context across long conversations?
- Context Window
- Memory Mechanisms
- Both A and B
- Neither
Answer: Both A and B
Long-context handling: larger context windows (128K+ tokens), memory mechanisms (summarization, retrieval) maintain conversation history. Critical for chatbots and assistants.
Which framework provides guidelines for ethical AI development adopted by India?
- OECD AI Principles
- UNESCO AI Ethics
- Both A and B
- Neither
Answer: Both A and B
India endorses OECD AI Principles (2019) and UNESCO Recommendation on AI Ethics (2021). Both emphasize human rights, transparency, accountability, sustainability. Critical for AI governance.
Which initiative provides a unified platform for startup mentoring, funding, and compliance?
- Startup India Hub
- DPIIT Recognition
- Both A and B
- Neither
Answer: Both A and B
Startup India ecosystem integrates: Hub for resources/networking, DPIIT recognition for benefits, NITI Aayog for policy. Supports innovation, job creation, global competitiveness.
Which technique handles time series forecasting with seasonal patterns?
- ARIMA
- Prophet
- LSTM
- All of these
Answer: All of these
Time series methods: ARIMA for stationary series, Prophet for seasonality/holidays, LSTM for complex patterns. Choice depends on data characteristics and forecast horizon.
Which visualization is best for comparing proportions of categories?
- Bar Chart
- Pie Chart
- Stacked Bar
- All of these
Answer: All of these
Proportion visualization: bar charts for clear comparison, pie charts for part-to-whole (limited categories), stacked bars for multiple groups. Choice depends on data and audience.
Which pattern enables gradual traffic shifting between application versions for safe deployments?
- Blue-Green
- Canary
- Feature Flags
- All of these
Answer: All of these
Safe deployment patterns: blue-green (instant switch), canary (gradual rollout), feature flags (toggle functionality). Combined for zero-downtime, low-risk releases. Critical for DevOps practices.
Which storage class is most cost-effective for infrequently accessed archival data?
- Standard
- Infrequent Access
- Archive
- Glacier Deep Archive
Answer: Glacier Deep Archive
Glacier Deep Archive offers lowest cost for long-term retention with 12+ hour retrieval times. Ideal for regulatory archives, backups. Trade-off: low storage cost vs high retrieval latency.
Which technique identifies compromised accounts by analyzing login patterns and behaviors?
- UEBA
- SIEM
- EDR
- All of these
Answer: UEBA
UEBA (User and Entity Behavior Analytics) uses ML to establish behavioral baselines and detect anomalies indicating compromised accounts or insider threats. Critical for identity security.
Which practice ensures ML models are tested for security vulnerabilities before deployment?
- Adversarial Testing
- Penetration Testing
- Both A and B
- Neither
Answer: Both A and B
ML security testing: adversarial examples test robustness, penetration testing finds implementation flaws. Critical for secure AI deployment in sensitive domains.
Which technique enables LLMs to generate code from natural language descriptions?
- Code LLMs
- Program Synthesis
- Both A and B
- Neither
Answer: Both A and B
Code LLMs (Codex, CodeLlama) trained on code corpora enable natural language to code generation. Program synthesis automates code creation from specifications. Critical for developer productivity tools.
Which body regulates telecommunications services and spectrum allocation in India?
- TRAI
- DoT
- TSDSI
- MeitY
Answer: TRAI
Telecom Regulatory Authority of India (TRAI) recommends policies, regulates tariffs, ensures QoS, and manages spectrum auctions. Critical for telecom sector governance questions.
Which technique handles high-cardinality categorical variables efficiently?
- One-Hot Encoding
- Target Encoding
- Embedding Layers
- All of these
Answer: All of these
High-cardinality handling: one-hot for low cardinality, target encoding for medium, embeddings for high (deep learning). Choice depends on model type and cardinality. Critical for feature preprocessing.
Which metric measures the ability of a classifier to distinguish between classes?
- Accuracy
- Precision
- ROC-AUC
- F1 Score
Answer: ROC-AUC
ROC-AUC (Receiver Operating Characteristic - Area Under Curve) measures classifier performance across all thresholds, robust to class imbalance. Critical for evaluating binary classification models.
Which disaster recovery strategy maintains a fully operational standby environment in another region?
- Backup and Restore
- Pilot Light
- Warm Standby
- Multi-Site Active-Active
Answer: Multi-Site Active-Active
Active-active runs full workload in multiple regions simultaneously, enabling instant failover with zero RPO/RTO. Highest cost but maximum resilience. Critical for mission-critical systems.