Correct Answer : John McCarthy
Explanation : John McCarthy, an American computer scientist pioneer and inventor, was called the “Father of Artificial Intelligence.” In his 1955 proposal for the 1956 Dartmouth Conference, the first artificial intelligence conference, the cognitive scientist coined the term. The intention was to see if there was a way to create a machine that could think abstractly, solve problems, and develop itself like a human. “Every aspect of learning or any other feature of intelligence can, in principle, be described so precisely that a machine can be made to simulate it,” he claimed.
Correct Answer : Marvin Minsky & John McCarthy
Explanation :
Correct Answer : Making a Machine Intelligent
Explanation : Artificial intelligence is the simulation of human intelligence processes by machines, especially computer systems. Specific applications of AI include expert systems, natural language processing, speech recognition and machine vision.
Correct Answer : the embodiment of human intellectual capabilities within a computer
Correct Answer : Small Search Space
Explanation : Blind Search is also known as uninformed search, and it does not contain any domain information such as closeness, location of the goal, etc. Hence the most appropriate situation that can be used for the blind search is Small-search Space.
Correct Answer : All of the above
Explanation : Philosophy, Sociology, Biology all three areas can contribute to build an intelligent system.
Correct Answer : cdr
Correct Answer : BACON
Correct Answer : FALSE
Explanation : A computer program with AI can answer the generic questions it is meant to solve.
Correct Answer : Unlimited memory
Explanation : There are four(4) types of artificial intelligence : reactive machines, limited memory, theory of mind and self-awareness.
Correct Answer : A statement is satisfiable if there is some interpretation for which it is true
Explanation : ‘Satisfiable’ property is a statement is satisfiable if there is some interpretation for which it is true.
Correct Answer : (sqrt x)
Correct Answer : Printed language and synthesized speech
Correct Answer : Cognitive Artificial Intelligence approach
Explanation : In the Cognitive Artificial Intelligence approach, a computer is used to test theories about how the human mind works, for example, theories about how we recognize faces and other objects, or about how we solve abstract problems.
Correct Answer : Dartmouth
Correct Answer : Carnegie Mellon University.
Explanation : John McCarthy coined the term Artificial Intelligence. Demonstration of the first running AI program at Carnegie Mellon University.
Explanation : Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think.
Correct Answer : They are identical but of opposite sign
Explanation : Two literals are complementary if They are identical but of opposite sign.
Correct Answer : Samples
Correct Answer : Sequence of test
Explanation : A decision tree is the supervised machine learning technique that can be used for both Classification and Regression problems. It reaches its destination using a Sequence of Tests.
Correct Answer : Symbolics
Correct Answer : Shakey
Correct Answer : speaking
Correct Answer : Representational Verification
Correct Answer : Manipulator
Correct Answer : Heuristic
Correct Answer : Language understanding and problem-solving (Text analytics and NLP)
Explanation : Language understanding and problem-solving come under the NLP and Text Analysis area which involves text recognition and sentiment analysis of the text. NLP ML model is trained to mainly do the task which processes human language’s speech or text. For example voice assistant.
Correct Answer : categorized into 3 categories
Explanation : Consider an excellent knowledge representation system for a specific topic. Representational Adequacy, Inferential Adequacy, Inferential Efficiency, and Acquisitional Efficiency should be the qualities.
Correct Answer : Depth-First Search
Correct Answer : Donald Michie
Correct Answer : Intelligent
Explanation : If a robot is able to change its own trajectory as per the external conditions, then the robot is considered intelligent. Such type of agents come under the category of AI agents or Rational Agents.
Correct Answer : The Explorer
Correct Answer : Performance
Correct Answer : Geology
Explanation : Geology can not contribute to build an intelligent system.
Correct Answer : Design
Correct Answer : algorithmic and heuristic
Correct Answer : relative symbolism
Correct Answer : contains procedural knowledge
Correct Answer : Speaker-dependent recognition
Correct Answer : hierarchical planning
Correct Answer : Both (a) and (b)
Explanation : Sensors are used to perceive from the environment and actuators are used to act on the environment by the system.
Correct Answer : 2
Correct Answer : Cognitive approach
Explanation : Cognitive approach is used to build a system which can behave and think like human beings and solve the problems.
Correct Answer : Applied approach
Explanation : Applied approach aims to produce commercially viable “smart” systems such as, for example, a security system that recognizes the faces of people to provide access. The applied approach has already enjoyed considerable success.
Explanation : Artificial intelligence creates a machine that can think and make decisions without human involvement.
Correct Answer : ILP
Explanation : ILP (Inductive Logic Programming) is a subfield of artificial intelligence. Because ILP can participate in the scientific cycle of experimentation So that it can produce a flexible structure.
Correct Answer : SHRDLU
Correct Answer : model-based vision
Correct Answer : Turing Test
Explanation : In the year 1950, mathematician and computing pioneer Alan Turing introduced a test to determine whether a machine can think like a human or not, which means it can demonstrate intelligence, known as the Turing Test. It was based on the "Imitation game" with some modifications. This technique is still a measure of various successful AI projects, with some updates.
Correct Answer : Min/Max algorithm
Explanation : A game tree is a directed graph whose nodes represent the positions in Game and edges represent the moves. To make any decision, the game tree uses the Min/Max algorithm. The Min/Max algorithm is the preferred one over other search algorithms, as it provides the best move to the player, assuming that the opponent is also playing Optimally.
Correct Answer : Condition-action rule
Explanation : The simple reflex agent takes decisions only on the current condition and acts accordingly; it ignores the rest of history; hence it follows the Condition-action rule.
Correct Answer : Smalltalk
Correct Answer : Detect when a solution has been found
Explanation : Third component of a planning system is to detect when a solution has been found.
Correct Answer : Current perception
Explanation : These agents select actions based on the current perception, ignoring the rest of the perception history.
Correct Answer : More characters
Correct Answer : ICOT (Institute for New Generation Computer Technology)
Correct Answer : Cognitive science
Correct Answer : Expert system
Correct Answer : Defense
Correct Answer : Business decisions
Correct Answer : Strong approach
Explanation : The goal of a strong approach is to create machines that can really think and solve problems. These machines must be self-aware, and their total cognitive aptitude must be comparable to that of a human person. Strong approach argues that robots can have cognitive mental states if they are properly developed.
Correct Answer : NaturalLink
Correct Answer : Ed Feigenbaum
Correct Answer : Applied Artificial Intelligence approach
Explanation : Applied Artificial Intelligence approach aims to produce commercially viable “smart” systems such as, for example, a security system that is able to recognize the faces of people who permitted to enter a particular building. Applied Artificial Intelligence has already enjoyed considerable success.
Correct Answer : human intelligence
Correct Answer : checkers
Explanation : In a heuristic approach, we discover certain idea and use heuristic functions to search for a goal and predicates to compare nodes.
Correct Answer : Û·x: dog(x) Ã hastail(x)
Explanation : We represent the statement in mathematical logic taking ‘x ‘as Dog and which has tail. We cannot represent two variable x, y for the same object Dog that has tail. The symbol “Û· “represent all.
Correct Answer : CRAY BLITZ
Correct Answer : frame-based CAI
Correct Answer : The probability that hypotheses Hi is true given evidence E
Correct Answer : Weak Artificial Intelligence approach
Explanation : Weak Artificial Intelligence deals with the creation of some form of computer-based artificial intelligence that cannot truly reason and solve problems, but can act as if it were intelligent. Weak Artificial Intelligence holds that suitably programmed machines can simulate human cognition.
Correct Answer : continuous-path control
Correct Answer : LISP
Correct Answer : LISP machines
Correct Answer : Fifth
Correct Answer : hydraulic
Correct Answer : Texas Instruments
Correct Answer : expert system
Correct Answer : MIMD
Correct Answer : Non-monotonic reasoning
Correct Answer : Ease with which the method can be adapted to different domains of application
Explanation : Generality is the measure of the ease with which the method can be adapted to different domains of application.
Correct Answer : What to say
Correct Answer : educational institutions
Correct Answer : Transition Network
Correct Answer : color and motion, depth and texture
Correct Answer : Design problem
Explanation : The design problem depends on the percepts and actions available to the agent, the goals that the agent’s behavior should satisfy.
Correct Answer : Perl
Explanation : Because Perl is used as a script language, and not of much use for AI practice. All others are used to generate an artificial program.
Correct Answer : Problem
Explanation : Task environments will pose a problem and rational agent will find the solution for the posed problem.
Correct Answer : Online search
Explanation : In online search, it will first take an action and then observes the environment.
Correct Answer : Sensors and Actuators
Explanation : An agent is anything that can be viewed as perceiving and acting upon the environment through the sensors and actuators.
Correct Answer : Target based
Explanation : The four types of agents are Simple reflex, Model based, Goal based and Utility based agents.
Correct Answer : An agent is anything that can perceive its environment through sensors
Explanation : An agent is anything that can perceive its environment through sensors and acts upon that environment through effectors
Correct Answer : Decision-making algorithm
Explanation : Decision-making and learning algorithms can operate over the joint state space and thereby serve to implement and used to improve the computational activities.
Correct Answer : MEMS
Explanation : Micro Electro Mechanical System(MEMS) uses miniaturized accelerometers and gyroscopes and is used to produce actuators.
Correct Answer : Performance Measure, Environment, Actuators, and Sensors
Explanation : The problem the agent solves is characterized by Performance Measure, Environment, Actuators, and Sensors (PEAS).
Correct Answer : Architecture + Agent Program
Explanation : Agent's structure can be viewed as - Agent = Architecture + Agent Program
Explanation : An environment is something which agent stays in.
Correct Answer : Fully Observable
Explanation : In crossword puzzle an agent knows the complete state of the environment through its sensors.
Correct Answer : Partially Observable
Explanation : System knows the current status of the analysis thought its inputs.
Correct Answer : Filtering algorithm
Explanation : Filtering algorithm is used for tracking uncertain events because in this the real perception is involved.
Correct Answer : Both Objects & Relations
Explanation : Objects and relations are not represented by using propositional logic explicitly.
Correct Answer : Deterministic
Explanation : If the environment is deterministic except for the action of other agent is called deterministic.
Correct Answer : Environment Generator
Correct Answer : Environment does not change with the passage of time, but Agent performance changes
Correct Answer : A goal state is reachable from every state
Correct Answer : Learning agent
Explanation : Simple reflex agent is based on the present condition and so it is condition action rule.
Correct Answer : Utility based agent
Explanation : A utility function maps a state onto a real number which describes the associated degree of happiness.
Correct Answer : Search & Plan
Explanation : When the environment becomes more tricky means, the agent needs plan and search action sequence to achieve the goal.
Correct Answer : No agent / Multiple agents
Correct Answer : Both RBFS & SMA*
Explanation : RBFE and SMA* will solve any kind of problem that A* can’t by using limited amount of memory.
Correct Answer : Representing your problem with variable and parameter
Explanation : Because state space is mostly concerned with a problem, when you try to solve a problem, we have to design a mathematical structure to the problem, which can only be through variables and parameters. eg. You have given a 4-gallon jug and another 3-gallon jug. Neither has measuring marker on it. You have to fill the jugs with water. How can you get exactly 2 gallons of water in to 4 gallons. Here the state space can defined as set of ordered pairs integers(x,y), such that x=0,1,2,3 or 4 and y=0,1,2 or 3; X represents the number of gallons in 4 gallon jug and y represents the quantity of water in the 3-gallon jug.
Correct Answer : Depth-first search
Explanation : It implements stack operation because it always expands the deepest node in the current tree.
Correct Answer : Problem Instance
Explanation : Problem Instance : It is Initial state + Goal state.
Correct Answer : b^d
Explanation : Time Complexity of Breadth First search algorithm is b^d.
Correct Answer : Uninformed Search
Explanation : In case of uninformed search no additional information except the problem definition is given.
Explanation : Several uninformed search techniques includes BFS, DFS, Uniform-cost, Depth-limited, Bidirectional search etc.
Correct Answer : Heuristic search
Correct Answer : Evaluation function returning lowest evaluation
Explanation : Best-first search is an instance of the general TREE-SEARCH or GRAPH-SEARCH algorithm in which a node is selected for expansion based on an evaluation function, f (n). Traditionally, the node with the lowest evaluation is selected for expansion, because the evaluation measures distance to the goal.
Correct Answer : The average number of child nodes in the problem space graph.
Explanation : Branching Factor : The average number of child nodes in the problem space graph.
Correct Answer : Abstraction
Explanation : The process of removing detail from a representation is called abstraction.
Correct Answer : Less memory & Finds a solution in large infinite space
Explanation : Two advantages: (1) they use very little memory-usually a constant amount; and (2) they can often find reasonable solutions in large or infinite (continuous) state spaces for which systematic algorithms are unsuitable.
Correct Answer : No neighbor has higher value
Correct Answer : Goal Based & Online agent
Correct Answer : Local Beam search
Correct Answer : Constraints Satisfaction Problems
Correct Answer : Forward Searching
Explanation : Forward Searching is technique in which a forward check till k steps is made to analyze that the goal can be achieved satiating all constraints. With constraint propagation, constraints on a variable can be propagated to next level/hierarchy and satisfied at that level, eliminating need to backtrack.
Correct Answer : CSP
Explanation : Schedule developer needs to consider all constraints on teacher as well as students.
Correct Answer : NP complete
Correct Answer : Constraints
Correct Answer : Both Last in first out & Recursion
Correct Answer : Depth-first search algorithm
Correct Answer : Bidirectional Search
Explanation : Bidirectional Search searches forward from initial state and backward from goal state till both meet to identify a common state.
Correct Answer : Best-First-Search
Explanation : Best-first-search is giving the idea of optimization and quick choose of path, and all these characteristic lies in A* algorithm.
Correct Answer : Estimated cost of cheapest path from root to goal node
Correct Answer : The one closest to the goal node
Explanation : Sometimes minimum heuristics can be used, sometimes maximum heuristics function can be used. It depends upon the application on which the algorithm is applied.
Correct Answer : Initial state
Explanation : A problem has four components initial state, goal test, set of actions, path cost.
Correct Answer : Tree algorithm
Explanation : Tree algorithm is used because specific variants of the algorithm embed different strategies.
Correct Answer : O(bm)
Explanation : O(bm) is the space complexity where b is the branching factor and m is the maximum depth of the search tree.
Correct Answer : Intelligent goal-based agent
Correct Answer : Set of Rule & sequence of steps
Explanation : When you are trying to solve a problem, you should design how to get a step-by-step solution with constraints condition to your problem, e.g Chess board problem.
Correct Answer : Heuristic approach (Some knowledge is stored)
Explanation : We use a Heuristic approach, as it will find out brute force computation, looking at hundreds of thousands of positions. e.g Chess competition between Human and AI based Computer.
Correct Answer : LIFO
Explanation : Depth-First Search implemented in recursion with LIFO stack data structure.
Correct Answer : It can get stuck in loops. It is not optimal.
Explanation : The disadvantage of Greedy Best First Search is that it can get stuck in loops. It is not optimal.
Correct Answer : 4
Explanation : The four types of informed search method are best-first search, Greedy best-first search, A* search and memory bounded heuristic search.
Correct Answer : 5
Explanation : The five types of uninformed search method are Breadth-first, Uniform-cost, Depth-first, Depth-limited and Bidirectional search.
Correct Answer : O(bd+1) and O(bd+1)
Explanation : We consider a hypothetical state space where every state has b successors. The root of the search tree generates b nodes at the first level, each of which generates b more nodes, for a total of b2 at the second level. Each of these generates b more nodes, yielding b3 nodes at the third level, and so on. Now suppose that the solution is at depth d. In the worst case, we would expand all but the last node at level d (since the goal itself is not expanded), generating bd+1- b nodes at level d+1.
Correct Answer : When all step costs are equal
Correct Answer : f(n) = h(n)
Correct Answer : Only Single-agent and Multi-agent
Explanation : Depending upon games it could be single agent (Sudoku) or multi-agent (Chess).
Correct Answer : Competitive Environment
Explanation : Since in cooperative environment agents’ goals are I conflicts. They compete for goal.
Correct Answer : Same as of DFS
Correct Answer : Multiplayer
Explanation : Zero sum games could be multiplayer games as long as the condition for zero sum game is satisfied.
Correct Answer : Pruned leaves x and y
Explanation : The minimax decision are independant of the values of the pruned values x and y because of the root values.
Correct Answer : 6 States
Explanation : Alpha–beta pruning can be applied to trees of any depth and it is possible to prune entire subtree rather than leaves.
Explanation : The minimax search is depth-first search, So at one time we just have to consider the nodes along a single path in the tree.
Correct Answer : Evaluation function
Explanation : Because we need to cut the search off at some point and apply an evaluation function that gives an estimate of the utility of the state.
Correct Answer : Hash table of previously seen positions
Correct Answer : Both Alpha = max & Beta = min
Explanation : Alpha and beta are the values of the best choice we have found so far at any choice point along the path for MAX and MIN.
Correct Answer : State-space search
Explanation : The straightforward approach for planning algorithm is state space search because it takes into account of everything for finding a solution.
Correct Answer : Both Preconditions & Effects
Explanation : The state-space search takes both precondition and effects into account for solving a problem.
Correct Answer : Progression planning
Explanation : It is sometimes called as progression planning, because it moves in the forward direction.
Correct Answer : Regression planning
Explanation : Backward state-space search will find the solution from goal to the action, So it is called as Regression planning.
Correct Answer : Termination
Correct Answer : Subgoal independence
Explanation : Subgoal independence approach is to pretend that a pure divide and conquer algorithm will work for admissible heuristics.
Correct Answer : Deductive Systems
Correct Answer : Atomic sentences
Correct Answer : Logical connectives
Explanation : The five logical symbols are negation, conjunction, disjunction, implication and biconditional.
Correct Answer : Semantics of propositional logic
Explanation : Because the meaning of the sentences is really needed to compute the truth.
Explanation : Logical inference algorithm can be solved be using logical equivalence, Validity and satisfiability.
Correct Answer : Resolution
Explanation : Because resolution yields a complete inference rule when coupled with any search algorithm.
Correct Answer : Unit clause
Correct Answer : Inference rule
Correct Answer : Propositional resolution
Correct Answer : Every sentence of first-order logic
Correct Answer : Original statement
Explanation : The CNF statement will be unsatisfiable just when the original sentence is unsatisfiable.
Correct Answer : Removal of redundant literal
Correct Answer : Sentence is unsatisfiable
Explanation : Resolution is refutation-complete, if a set of sentence is unsatisfiable, then resolution will always be able to derive a contradiction.
Correct Answer : Reduced to one
Explanation : Propositional factoring reduces two literals to one if they are identical.
Correct Answer : No further inference
Explanation : Forward chain can grow by adding new atomic sentences until no further inference is made.
Correct Answer : First-order definite clauses
Correct Answer : Conjunct ordering
Explanation : Conjunct ordering will find an ordering to solve the conjuncts of the rule premise so that the total cost is minimized.
Correct Answer : New fact
Correct Answer : First-order definite clause are similar to propositional forward chaining
Explanation : Fixed point reached by forward chaining with first-order definiteclause are similar to those for propositional forward chaining.
Correct Answer : Generalized modus ponens
Explanation : Definite clauses are a suitable normal form for use with generalized modus ponen.
Correct Answer : Universally quantified
Explanation : First-order literals will accept variables only if they are universally quantified.
Correct Answer : Backward chaining
Explanation : Backward chaining algorithm will work backward from the goal and it will chain the known facts that support the proof.
Correct Answer : Substitutes matching the query
Explanation : It will contains the list of goals containing a single element and returns the set of all substitutions satisfying the query.
Correct Answer : Stack
Explanation : The goals can be thought of as stack and if all of them us satisfied means, then current branch of proof succeeds.
Explanation : It is depth-first search algorithm because its space requirements are linear in the size of the proof.
Correct Answer : Expressing knowledge in a formal language
Explanation : Logic programming can be constructed by expressing knowledge in a formal expression and the problem can be solved by running inference process.
Correct Answer : Occur check
Explanation : Occur check is omitted in prolog unification algorithm because of unsound inferences.
Correct Answer : Both Repeated states & Incompleteness
Correct Answer : Logic programming
Explanation : Logic programming is mainly used to check the working process of the system.
Explanation : Knowledge and reasoning could aid to reveal other factors that could complete environment.
Correct Answer : Reasoning with Knowledge
Explanation : Refer the definition of Wumpus World Problem.
Correct Answer : It can derive any sentence that is an entailed version & It is truth preserving
Correct Answer : Unification
Explanation : Refer the definition if universal instantiation.
Correct Answer : Reduction to propositional logic, Manipulate rules directly
Correct Answer : Crown(Venkat) ^ OnHead(Venkat, Raja)
Correct Answer : Modus Ponen
Explanation : Modus ponen is a rule for an inference.
Correct Answer : Data-driven, Goal-driven
Correct Answer : And/Or Trees
Correct Answer : MYSIN
Correct Answer : Inference Engine & Knowledge Base
Explanation : Look at the general architecture of rule based expert systems.
Correct Answer : True
Correct Answer : A way of representing knowledge
Correct Answer : Intersection Search
Correct Answer : B has A as a part of itself
Correct Answer : Directed graph
Explanation : Semantic Network is a directed graph consisting of vertices, which represent concepts and edges, which represent semantic relations between the concepts.
Correct Answer : A is part of B
Correct Answer : Partitioned Networks
Correct Answer : A denotes opposite of B
Correct Answer : Wordnet
Explanation : Wordnet is a lexical database of English.
Correct Answer : A denotes same as B
Correct Answer : Lack in expressing some of the properties
Correct Answer : Facts or Data
Correct Answer : Hashes
Explanation : The buckets can be stored in a hash table for efficient access.
Explanation : The four functions are available in the unification and lifting process are tell, ask, store and fetch.
Correct Answer : Generalized Modus Ponens
Explanation : All kinds of inference process can be captured as a single inference rule that can be called as Generalized modus ponens.
Correct Answer : Unify algorithm
Explanation : The unify algorithm takes two sentences and returns a unifier if there is one in the sentence.
Correct Answer : Most general unifier
Explanation : For every unifiable pair of expressions, there is a single most general unifier that is unique up to renaming of variables.
Explanation : Occur check makes the complexity of the entire algorithm quadratic in the size of the expressions being unified.
Correct Answer : Knowledge base
Explanation : The simplest way to implement store and fetch functions is to keep all the facts in the knowledge base in one long list.
Explanation : Generalized modus ponens is a lifted version of modus ponens because it raises modus ponens from propositional to first-order logic.
Correct Answer : Partial & local Information
Explanation : The Wumpus world is a grid of squares surrounded by walls, where each square can contain agents and objects. The agent (you) always starts in the lower left corner, a square that will be labeled [1, 1]. The agent’s task is to find the gold, return to [1, 1] and climb out of the cave. Therefore, uncertainty is there as the agent gives partial and local information only. Global variable are not goal specific problem solving.
Correct Answer : Hierarchical plan
Explanation : A plan that describes how to take actions in levels of increasing refinement and specificity is Hierarchical (e.g., “Do something” becomes the more specific “Go to work,” “Do work,” “Go home.”) Most plans are hierarchical in nature.
Correct Answer : Partial order planning
Correct Answer : Forward state-space search
Explanation : Forward and backward state-space search are particular forms of totally ordered plan search.
Correct Answer : Least commitment
Explanation : The general strategy of delaying a choice during search is called the least commitment strategy.
Correct Answer : Most-constrained variable
Explanation : The most-constrained variable heuristic from CSPs can be adapted for planning algorithm and seems to work well.
Correct Answer : Effect
Explanation : Finish has no effects and has as its preconditions the goal literals of the planning algorithm.
Correct Answer : Both Start & Finish
Explanation : The "empty" plan contains just the start and finish actions.
Correct Answer : Partial-order planner
Explanation : Any planning algorithm that can place two actions into a plan without specifying which should come first is called partial-order planner.
Correct Answer : Problem decomposition
Explanation : As the search explore only linear sequences of actions, So they cannot take advantage of problem decomposition.
Correct Answer : 6
Explanation : The partial-order solution corresponds to six possible total-order plans.
Correct Answer : Planning graph algorithm
Explanation : A special data structure called planning graph is used to give better heuristic estimates.
Correct Answer : If two literals are negation of other
Explanation : If two literals are at the same level if one is the negation of another is called inconsistent support.
Correct Answer : Identical
Correct Answer : Graphplan
Explanation : We can extract the solution directly from the planning graph, using a specialized algorithm called Graphplan.
Correct Answer : Sequence of levels
Correct Answer : Propositional planning problem
Explanation : Planning graph work only for propositional planning problem with no variables.
Correct Answer : Level 0
Correct Answer : Planning problem
Correct Answer : Execution monitoring
Explanation : It assumes complete and correct information, deterministic and fully-observable environment, which many domains violates.
Correct Answer : SatPlan
Explanation : The SATPLAN algorithm translates a planning problem into propositional axioms and applies a satisfiability algorithm to find a model that corresponds a valid plan.
Correct Answer : Hierarchical task network (HTN)
Correct Answer : Linearization
Explanation : Each and every total order plan is also called as linearization of the partial-order plan.
Correct Answer : Planning Graphs
Explanation : A planning graph can be used to give better heuristic estimates.
Correct Answer : Search & Logic
Correct Answer : Both discrete and continuous variables
Explanation : To specify a Hybrid network, we have to specify two new kinds of distributions: the conditional distribution for continuous variables given discrete or continuous parents, and the conditional distribution for a discrete variable given continuous parents.
Correct Answer : IF and THEN Approach
Explanation : FL incorporates a simple, rule-based IF X AND Y THEN Z approach to a solving control problem rather than attempting to model a system mathematically.
Correct Answer : Decision Theory = Uncertainty + utility theory
Correct Answer : A false positive hypothesis
Explanation : Consistent hypothesis go with examples, If the hypothesis says it should be negative but in fact it is positive, it is false negative. If a hypothesis says it should be positive, but in fact it is negative, it is false positive. In a specialized hypothesis we need to have certain restrict or special conditions.
Correct Answer : Semantic
Explanation : Semantic analysis is used to extract the meaning from the group of sentences.
Correct Answer : Determining the meaning
Explanation : Compositional semantics is the process of determining the meaning of P*Q from P, Q and *.
Correct Answer : Pragmatic
Correct Answer : Intermediate form
Correct Answer : Weighted sum of the shape
Explanation : The distance between two shapes can be defined as a weighted sum of the shape context distance between corresponding points.
Correct Answer : Bottom-up segmentation
Explanation : In the process of creating subset of pixels, the bottom-up segmentation is an error-prone process.
Correct Answer : Vision
Explanation : Vision enables people to recognize people, animals and inanimate objects reliably. It is customary to use object recognition.
Correct Answer : Both Objects & Activities
Explanation : Vision is used to recognize not only objects, but also activities.
Correct Answer : Shape context
Explanation : Because an object’s shape can be manipulated with respect to the point.
Correct Answer : Learning
Correct Answer : Supervised learning
Explanation : Supervised learning or pattern classification provides a framework for studying object recognition.
Correct Answer : Deformable matching
Explanation : The main issues for degree of belief are nature of the sentences and the dependance of degree of the belief.
Correct Answer : Propositions
Correct Answer : Random variable
Explanation : The basic element for a language is the random variable, which can be thought as a part of world and its status is initially unknown.
Correct Answer : Probability distributions for Continuous variables
Correct Answer : Atomic event
Explanation : An atomic event is the complete specification of the state of the world about which the event is uncertain.
Correct Answer : Continuous
Explanation : For continuous variables, it is not possible to write out the entire distribution as a table.
Correct Answer : 3
Explanation : The three required terms are a conditional probability and two unconditional probability.
Correct Answer : Using information
Explanation : Every entry in the full joint probability distribution can be calculated from the information in the network.
Correct Answer : Conditionally independent
Explanation : The semantics to derive a method for constructing bayesian networks were led to the consequence that a node can be conditionally independent of its predecessors.
Correct Answer : Linear
Explanation : Local structure is usually associated with linear rather than exponential growth in complexity.
Correct Answer : Joint distribution
Explanation : If a bayesian network is a representation of the joint distribution, then it can solve any query, by summing all the relevant joint entries.
Correct Answer : Crucial robustness
Explanation : On a model-based knowledge provides the crucial robustness needed to make probabilistic system feasible in the real world.
Correct Answer : Many-valued logic
Explanation : With fuzzy logic set membership is defined by certain value. Hence it could have many values to be in the set.
Correct Answer : Fuzzy Set
Explanation : Fuzzy logic deals with linguistic variables.
Explanation : The AND, OR, and NOT operators of Boolean logic exist in fuzzy logic, usually defined as the minimum, maximum, and complement;
Correct Answer : IF-THEN rules
Correct Answer : Hedges
Correct Answer : Degree of truth
Correct Answer : Hidden markov model
Explanation : Hidden Markov model is used for solving temporal probabilistic reasoning that was independent of transition and sensor model.
Correct Answer : Possible states of the world
Explanation : The possible values of the variables are the possible states of the world.
Correct Answer : Temporal model
Explanation : Additional state variables can be added to a temporal model while staying within the HMM framework.
Correct Answer : Restricted structure of HMM
Explanation : Restricted structure of HMM allows for a very simple and elegant matrix implementation of all the basic algorithm.
Correct Answer : Constant space
Correct Answer : Modified smoothing
Explanation : The modified smoothing algorithm works by first running the standard forward pass to compute and then running the backward pass.
Correct Answer : Speech recognition
Correct Answer : STUDENT
Correct Answer : human factors
Correct Answer : information
Correct Answer : binary
Correct Answer : Feedback
Explanation : The type of feedback is used in determining the nature of the learning problem that the agent faces.
Correct Answer : Linear weighted polynomial
Explanation : Linear weighted polynomial is used for learning element in the game playing programs.
Correct Answer : Learning element
Explanation : A learning element modifies the performance element so that it can make better decision.
Correct Answer : Reinforcement learning
Explanation : Reinforcement learning is the type of learning in which teacher returns reward or punishment to learner.
Correct Answer : Unsupervised learning
Explanation : In unsupervised learning, no teacher is available hence it is also called unsupervised learning.
Correct Answer : None of the above
Explanation : In automatic vehicle set of vision inputs and corresponding actions are available to learner hence it’s an example of supervised learning.
Correct Answer : Good data structures
Explanation : Factors which affect the performance of learner system does not include good data structures.
Correct Answer : Introduction
Explanation : Different learning methods include memorization, analogy and deduction.
Correct Answer : Attachment
Correct Answer : Specific output values are not given
Explanation : The problem of unsupervised learning involves learning patterns in the input when no specific output values are supplied. We cannot expect the specific output to test your result. Here the agent does not know what to do, as he is not aware of the fact what propose system will come out. We can say an ambiguous un-proposed situation.
Correct Answer : Not all formal languages are context-free
Explanation : Not all formal languages are context-free.
Correct Answer : Feed-forward neural network
Explanation : A perceptron is a Feed-forward neural network with no hidden units that can be representing only linear separable functions. If the data are linearly separable, a simple weight updated rule can be used to fit the data exactly.
Correct Answer : Inductive learning
Explanation : Computational learning theory analyzes the sample complexity and computational complexity of inductive learning. There is a tradeoff between the expressiveness of the hypothesis language and the ease of learning.
Correct Answer : Nonlinear Functions
Explanation : Neural networks parameters can be learned from noisy data and they have been used for thousands of applications, so it varies from problem to problem and thus use nonlinear functions.
Correct Answer : Consistent Hypothesis
Explanation : Inductive learning involves finding a consistent hypothesis that agrees with examples. The difficulty of the task depends on the chosen representation.
Correct Answer : a single layer feed-forward neural network with pre-processing
Explanation : The perceptron is a single layer feed-forward neural network. It is not an auto-associative network because it has no feedback and is not a multiple layer neural network because the pre-processing stage is not made of neurons.
Correct Answer : a neural network that contains feedback
Explanation : An auto-associative network is equivalent to a neural network that contains feedback. The number of feedback paths(loops) does not have to be one.
Correct Answer : It is powerful and easy neural network
Correct Answer : Because it is the simplest linearly inseparable problem that exists.
Correct Answer : It can explain result
Explanation : The artificial Neural Network (ANN) cannot explain result.
Explanation : All mentioned options are applications of Neural Network.
Correct Answer : Recurrent neural network
Explanation : RNN (Recurrent neural network) topology involves backward links from output to the input and hidden layers.
Correct Answer : Linear Functions
Explanation : Neural networks are complex linear functions with many parameters.
Correct Answer : Decision tree
Correct Answer : Triangles
Correct Answer : Squares
Correct Answer : Circles
Correct Answer : Inductive Logic Programming
Explanation : Inductive logic programming(ILP) combines inductive methods with the power of first-order representations.
Correct Answer : Three-dimensional configuration of a protein molecule
Correct Answer : Top-down approach
Correct Answer : Inverse resolution
Explanation : Because it is a complete algorithm for learning first-order theories.
Correct Answer : Attribute-based system
Explanation : ILP methods can learn relational knowledge that is not expressible in attribute-based system.
Explanation : Because ILP can participate in the scientific cycle of experimentation, So that it can produce flexible structure.
Correct Answer : Languages
Explanation : Language is the complex system of structured message that enables us to communicate.
Correct Answer : Formal language
Explanation : A formal language is defined by a set of strings that is a concatenation of terminal symbols.
Correct Answer : Encode semantic information into a syntactic grammar
Explanation : Semantic grammars encode semantic information into a syntactic grammar.
Correct Answer : Building a parse tree
Explanation : Parsing is the process of building a parse tree for an input string.
Correct Answer : Grammar
Correct Answer : Perception
Correct Answer : The halo effect
Correct Answer : Self-serving bias
Correct Answer : information processing that relies heavily on familiar schemata
Correct Answer : Recognize the people, objects, and situations remain stable over time
Correct Answer : Schematas
Correct Answer : Speech
Explanation : Speech is the dominant modality for communication between humans and reliable speech recognition between machines.
Correct Answer : Coarticulation effects
Explanation : Coarticulation effects are partially captured by triphone model, which can be manipulated by acoustic model.
Correct Answer : Three-state phone mone
Correct Answer : Phonology
Explanation : Speech recognition is viewed as problem of probabilistic inference because different words can sound the same.
Correct Answer : Bigram model
Explanation : Bigram model gives the probability of each word following each other word in speech recognition.
Correct Answer : Frames
Explanation : Speech system summarize the properties of the signal that extend over interval called frames.
Explanation : Perception provides agents with information about the world they inhabit.
Correct Answer : Photometry
Correct Answer : Smoothing
Explanation : Smoothing meant predicting the value of a state variable from the past and by given evidence and calculating the present and future.
Correct Answer : Canny edge detection
Explanation : Canny edge detection is assuming any two neighboring that are both edge pixels with consistent orientation and must belong to the same edge.
Explanation : The five types of 3-D image processing techniques are motion, binocular stereopsis, texture, shading and contour.
Correct Answer : Amount of light
Explanation : The brightness of a pixel in the image is proportional to the amount of light directed towards the camera.
Correct Answer : feedback
Correct Answer : business decisions
Correct Answer : controller
Correct Answer : private homes
Correct Answer : peripheral tools
Correct Answer : roll
Correct Answer : work envelope
Correct Answer : degrees of freedom
Correct Answer : pneumatic
Correct Answer : Low costs for hardware and software
Correct Answer : MIT
Correct Answer : robots must never take actions harmful to humans
Correct Answer : CMU
Correct Answer : production rules
Correct Answer : Converts one human language to another
Explanation : The best known example of machine translation is google translator.
Correct Answer : Separate words into individual morphemes and identify the class of the morphemes
Correct Answer : Handling Ambiguity of Sentences
Explanation : A Bayesian network provides a complete description of the domain.
Correct Answer : Word Sense Disambiguation
Explanation : Shallow Semantic Analysis doesn’t cover word sense disambiguation.
Correct Answer : Stemming
Correct Answer : batch processing
Correct Answer : LOGO
Correct Answer : (consp)
Correct Answer : intelligent
Correct Answer : (setq y ‘x’)
Correct Answer : (setq a 10)
Correct Answer : MACSYMA
Correct Answer : isolated word recognition
Correct Answer : A.M. Turning
Correct Answer : intelligent programming tools
Correct Answer : AI workstations
Correct Answer : artificial intelligence
Correct Answer : speaker independence
Correct Answer : natural language processing
Correct Answer : Study of communication between human and machine
Explanation : Cybernetics is Study of communication between human and machine.
Correct Answer : The entire tree so far been generated must be stored in BFS
Explanation : Regarding BFS-The entire tree so far been generated must be stored in BFS.
Correct Answer : It is guaranteed to return an optimal solution when one exists
Correct Answer : O(n!)
Explanation : The traveling salesman problem involves n cities with paths connecting the cities. The time taken for traversing through all the cities, without knowing in advance the length of a minimum tour, is O(n!).
Correct Answer : To explain various sorts of intelligence
Explanation : The scientific goal of artificial intelligence is to explain various sorts of intelligence.
Correct Answer : It terminates with a solution when one exists
Correct Answer : color and motion
Correct Answer : Both LMI & Symbolics
Correct Answer : seeing
Correct Answer : SIMD
Correct Answer : A mouse and specialized keyboard, Letter quality printers and eight-inch disk drives
Correct Answer : (+1.25 sqrt (1.44)
Correct Answer : Influence diagram
Explanation : The generalized form of Bayesian network that represents and solve decision problems under uncertain knowledge is known as an Influence diagram
Correct Answer : Dynamic Bayesian networks
Explanation : Dynamic Bayesian networks (DBNs) are used for modeling times series and sequences.
