61. What is Natural Language Generation (NLG) in AI?
- The process of converting spoken language into written text automatically
- A branch of NLP focused on automatically generating coherent, meaningful natural language text from structured data, knowledge bases, or other non-linguistic inputs
- A technique for generating synthetic language training data for NLP models
- The process of translating text from one natural language to another
Answer : B Explanation: Natural Language Generation (NLG) is the AI task of producing human-readable text from structured data or representations. NLG systems convert data (like sports scores or financial reports) into narratives, generate product descriptions, create weather forecasts, produce medical reports, and power conversational AI responses. Modern LLMs like ChatGPT and Claude are extremely powerful NLG systems. NLG is one of the two main directions of NLP — the other being NLU (Natural Language Understanding), which involves comprehending text. Together they enable full conversational AI.
62. What is the Travelling Salesman Problem (TSP) in AI?
- A problem about finding the fastest route for sales representatives using GPS
- A classic NP-hard combinatorial optimization problem that asks for the shortest possible route that visits each city exactly once and returns to the starting city
- A logistics problem solved using simple greedy algorithms in polynomial time
- A scheduling problem that assigns salespeople to territories using linear programming
Answer : B Explanation: The Travelling Salesman Problem (TSP) is one of the most famous NP-hard optimization problems in computer science and AI. Given a list of cities and the distances between them, the goal is to find the shortest route that visits each city exactly once and returns to the origin. The number of possible routes grows factorially with the number of cities — making brute force impossible for large inputs. AI techniques for solving TSP include Genetic Algorithms, Simulated Annealing, Ant Colony Optimization, and Dynamic Programming (Held-Karp algorithm). TSP has real applications in logistics and circuit board manufacturing.
63. What is Sentiment Analysis in AI?
- An AI technique for analyzing the emotional state of a robot during operation
- An NLP technique that identifies and extracts subjective information — such as opinions, emotions, and attitudes — from text to determine whether it is positive, negative, or neutral
- A computer vision technique for detecting emotions from facial expressions in images
- A data analysis technique used to measure customer sentiment from survey response rates
Answer : B Explanation: Sentiment Analysis (also called Opinion Mining) uses NLP and machine learning to determine the emotional tone of text. It classifies text as positive, negative, or neutral, and can also detect specific emotions (joy, anger, sadness) or aspect-specific sentiments (e.g., “the food was great but the service was terrible”). Applications include: brand reputation monitoring on social media, analyzing product reviews on Amazon, financial market sentiment from news, political opinion analysis, and customer feedback classification. Modern sentiment analysis uses BERT and other transformer models for high accuracy.
64. What is Hill Climbing in AI search?
- A search algorithm that always starts from the goal state and works downward
- A local search algorithm that continuously moves toward the neighbor with the highest value, attempting to find the global maximum but can get stuck in local maxima
- A tree search algorithm that only explores nodes at increasing depth levels
- A divide-and-conquer search method that splits the search space in half at each step
Answer : B Explanation: Hill Climbing is a local search algorithm that starts from a random initial state and iteratively moves to a neighboring state with a better value (higher “altitude”), like climbing a hill. It is simple and memory-efficient but has major weaknesses: it can get stuck in local maxima (peaks that are not the global maximum), plateaus (flat regions with no improvement), and ridges. Variants include Stochastic Hill Climbing (randomly selects among uphill moves) and Simulated Annealing (sometimes accepts worse moves to escape local maxima). Hill Climbing is used in optimization problems like the 8-queens puzzle.
65. What is Propositional Logic in AI?
- A mathematical framework where AI proposals are evaluated by committee vote
- A formal system of logic that deals with propositions (statements that are either true or false) and logical connectives such as AND, OR, NOT, and IMPLIES
- A programming paradigm used to propose new AI architectures to research teams
- A natural language processing technique for identifying key propositions in text
Answer : B Explanation: Propositional Logic (also called Boolean Logic or Sentential Logic) is the simplest form of formal logic used in AI for knowledge representation and reasoning. It uses propositions (statements that are true or false) connected by logical operators: AND (∧), OR (∨), NOT (¬), IMPLIES (→), and BICONDITIONAL (↔). Propositional logic can be used to encode knowledge and derive new facts through inference rules like Modus Ponens. However, it cannot represent relationships between objects — that limitation is addressed by First-Order Logic (Predicate Logic), which adds quantifiers and variables.
66. What is First-Order Logic (FOL) in AI and how does it differ from Propositional Logic?
- FOL deals with first-order derivatives; Propositional Logic deals with second-order derivatives
- First-Order Logic extends Propositional Logic by adding objects, predicates, functions, and quantifiers (∀ for all, ∃ there exists), enabling more expressive knowledge representation
- FOL uses binary values; Propositional Logic uses continuous probability values
- There is no meaningful difference — both systems represent knowledge identically
Answer : B Explanation: First-Order Logic (FOL), also called Predicate Logic, is more expressive than Propositional Logic. While Propositional Logic deals only with true/false statements, FOL introduces: Objects (individuals in the world), Predicates (properties of objects or relations between them), Functions (mappings from objects to objects), and Quantifiers (∀ = “for all”, ∃ = “there exists”). Example: ∀x (Human(x) → Mortal(x)) means “all humans are mortal.” FOL is the basis for PROLOG, description logics, and semantic web technologies. It is the primary knowledge representation language for AI reasoning systems.
67. What is Robotics in the context of Artificial Intelligence?
- The study of fictional robots in science fiction and their impact on society
- A branch of AI and engineering concerned with designing, building, and programming robots that can sense their environment, make decisions, and perform physical tasks autonomously
- The manufacture of computer hardware components using automated assembly lines
- A field that studies only the mechanical movement of industrial machinery
Answer : B Explanation: AI Robotics combines artificial intelligence with mechanical engineering to create machines that can perceive, reason, and act in physical environments. AI-powered robots use computer vision (to see), NLP (to communicate), reinforcement learning (to learn tasks), and sensor fusion (to navigate). Applications include: industrial manufacturing robots (welding, assembly), surgical robots (da Vinci), autonomous vehicles, drone delivery, humanoid robots (Boston Dynamics Atlas), agricultural robots, and household robots (Roomba). Modern AI robots use deep learning to handle unstructured, real-world environments.
68. What is a chatbot in AI?
- A robot that physically interacts with customers in retail stores
- An AI software application designed to simulate human conversation through text or voice, responding to user inputs to perform tasks or provide information
- A batch processing tool that automatically processes customer data overnight
- A social media monitoring tool that tracks brand mentions across platforms
Answer : B Explanation: A chatbot is an AI application that simulates human conversation. Rule-based chatbots follow predefined scripts and decision trees. AI chatbots use NLP and machine learning to understand intent and generate contextual responses. Modern LLM-based chatbots (ChatGPT, Claude, Gemini) can handle complex, open-ended conversations, write code, analyze documents, and more. Chatbots are widely deployed for customer service (handling FAQs, complaints), e-commerce (product recommendations), healthcare (symptom checking), banking (balance queries), and education (tutoring). They reduce operational costs while improving availability and response speed.
69. What is speech recognition in AI?
- A technology that converts written text into synthesized human-like speech output
- A technology that converts spoken language into written text using AI and signal processing techniques
- A biometric system that identifies individuals by the sound of their voice only
- A music AI technique that separates individual instruments from mixed audio recordings
Answer : B Explanation: Speech Recognition (also called Automatic Speech Recognition — ASR) converts spoken words into written text. Modern systems use deep learning (recurrent neural networks, transformers) trained on massive audio datasets. Key steps: audio signal processing, acoustic modeling, language modeling, and decoding. Applications include: virtual assistants (Siri, Alexa, Google Assistant), voice-to-text transcription, voice-controlled devices, call center automation, and accessibility tools for people with disabilities. OpenAI’s Whisper is a highly accurate open-source speech recognition model. The complementary technology is Text-to-Speech (TTS) which goes in the opposite direction.
70. What is an Autonomous Vehicle in the context of AI?
- A vehicle that runs on autonomous (self-generated) electricity without external charging
- A vehicle that uses AI, computer vision, sensors, and machine learning to navigate and drive without human input, perceiving its environment and making real-time driving decisions
- A remotely controlled vehicle operated by an AI system located in a data center
- A vehicle with automatic transmission that adjusts gears using a simple rule-based system
Answer : B Explanation: Autonomous Vehicles (self-driving cars) use a combination of AI technologies: Computer Vision (detecting objects, pedestrians, signs), LiDAR and RADAR (mapping surroundings in 3D), GPS (localization), Deep Learning (object classification and decision-making), and Reinforcement Learning (behavior planning). The SAE defines 6 automation levels (0-5), with Level 5 being fully autonomous. Tesla Autopilot, Waymo, and Cruise are leading examples. Key AI challenges include edge cases, sensor reliability, interpretability of decisions, and regulatory approval for public roads.
