* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download CS607_Midterm_Spring20151
Survey
Document related concepts
Pattern recognition wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Collaborative information seeking wikipedia , lookup
Machine learning wikipedia , lookup
Genetic algorithm wikipedia , lookup
Human–computer interaction wikipedia , lookup
Ecological interface design wikipedia , lookup
Philosophy of artificial intelligence wikipedia , lookup
Computer Go wikipedia , lookup
Personal knowledge base wikipedia , lookup
Embodied cognitive science wikipedia , lookup
Transcript
CS607 ALL Current Mid Term Papers Fall 2015 & Past Mid Term Papers at One Place from 20 JUNE 2015 to 01 JULY 2015 An Ai system must form a meaningful and usefull ______ of the internal information Representation Execution Planning Learning ______ reasoning is an informal form of reasoning that uses rules gained through experience or what we call rules-of-thumb Inductive Deductive Abductive Common-sense The components of a statement in CNF are Clauses and literals clauses Clauses Literals Frames An ______ is “A computer program designed to model the problem solving ability of a human expert” Expert system Intelligent system Echo system Energy system From discipline of ______ we have the tools and techniques to investigate the human mind and ways to represent the resulting theories. Computer science Biology Math Psychology In Depth first search, the node with the largest value of height will be picked _____ First Last Randomly None of the given Breadth-First search requires a great deal of ______ If the branching factor is large or infinite, because of exponential explosion Energy Space Care None of the given Best first search is a ___ approach Greedy Generous Optimized None of the given In adversarial search, the goals of the adversaries are usually ___ to each other Same Contrary Parallel None of the given Genetic Algorithm can be applied to ___ problems All Real Selected None of the fiven ____ were developed from semantic networks later evolved into modern day classes and objects Logic Networks Frames None of the given ____ is based on deducing old information from logically related known information Inductive Deductive Abductive Analogical An expert system named ____ was developed by digital equipment corporation as a computer assistant R1/Xcon MyCin Dendral R3/Xcon _____ chaining, is like an exhaustive search Forward Backward Parallel Serial Most of the solution for problems can be represented in a _____ Graph Table Demo Algorithm Which of the following does not make hill climbing hard Foothills Ridges Plateaus Slopes Intelligence is the ability to Recognize/ Remember Solve Learn All of the given options ____ AI treats the brain as a black box and just emulates its functionality Weak Strong Soft None of the given options Luger and stubblefield defined AI as “The branch of computer science that is concerned with the _____ of intelligent behaviour” Perception Automation Understanding Explanation An expert system reasons ______ by encoding an experts’s rule-of-thumb Heuristically Drastically efficiently None of the given 1. Perception and Knowledge Representation definition. 2 marks Ans: Perception component that allows the system to get information from its environment Knowledge representation maybe static or it may be coupled with a learning component that is adaptive and draws trends from the perceived data. 2. clips command to remove only facts. 2 marks Ans: The retract command is used to remove or retract facts. For example: (retract 1) removes fact 1(retract 1 3) removes fact 1 and 3 3. main people involved in an expert system. 3 marks Ans: The main people involved in an ES development project are the domain expert, the knowledge engineer and the end user. 4. perception and knowledge representation are coupled, yes or no with reason. 3 marks Solution: (Page 89) An AI system has a perception component that allows the system to get information from its environment. As with human perception, this may be visual, audio or other forms of sensory information. The system must then form a meaningful and useful representation of this information internally. This knowledge representation maybe static or it may be coupled with a learning component that is adaptive and draws trends from the perceived data. 5. a student wants to understand Expert System. explain to him. 5 marks Ans: According to Durkin, an expert system is “A computer program designed to model the problem solving ability of a human expert”. With the above discussion of experts in mind, the aspects of human experts that expert systems model are the experts: • Knowledge • Reasoning 6. apply GA to solve the following problem suppose our individual have 32 bit computer word, we want a word which all bits are zeros? 5 marks Ans: Create 100 randomly generated computer words • Repeatedly do the following: Count the 0 bits in each word • Exit if any of the words have all 32 bits set to 0 • Keep the ten words that have the most 0s (discard the rest) • From each word, generate 9 new words as follows: • Pick a random bit in the word and toggle (change) it • Note that this procedure does not guarantee that the next “generation” will have more 0 bits, but it‟s likely ----------Today’s paper of cs607. Q.How can you elaborate the usage of “defrule” in clips?__(2) Ans: Defrule command is used to add rules but using component rules facts must be defined first IF Ahmad is Ali’s Father than Ali is Ahmad’s Son CLIPS> (defrule isSon) Q.Difference b/w meta knowledge and heuristic knowledge .__(2) Ans: Meta knowledge: Knowledge about knowledge, e.g., the knowledge that blood pressure is more important for diagnosing a medical condition than eye color. Heuristic knowledge: Rule-of-thumb, e.g. if I start seeing shops, I am close to the market. 1. Heuristic knowledge is sometimes called shallow knowledge. 2. Heuristic knowledge is empirical as opposed to deterministic Q.Which algorithm is best when we don’t exactly know the initial goal state and operators?__(3) Ans: Q.How programming of experts system is different from conventional program.?__(5) Q.A student wants to get knowledge about forward chaing.how can you elaborate it ?__(5) Ans: Forward Chaining Let‟s look at how a doctor goes about diagnosing a patient. He asks the patient for symptoms and then infers diagnosis from symptoms. Forward chaining is based on the same idea. It is an “inference strategy that begins with a set of known facts, derives new facts using rules whose premises match the known facts, and continues this process until a goal sate is reached or until no further rules have premises that match the known or derived facts” (Durkin). As you will come to appreciate shortly, it is a data-driven approach. ----------2. write any 2 names of systems 2 marks Ans: expert system and conventional system, fuzzy system ---------my mid CS607 ppr 19-1-15 11 am Most of the mcqs from past pprs. Name any two tools/shells used in AI. 2marks diff between monotonic and non monotonic reasoning? 2marks Do you think inductive reasoning is based on deducing new information from logically known information. Give reason why? 3 marks Elaborate the importance of Knowledge Base in ES. (3 Marks) Draw structure of expert system. 5marks "Riding a Horse is same as Riding a Donkey" , This Statement belongs which reasoning...elaborate it (5 Marks) Remember me in ur prayers. ---------- Can anybody answer this question plz........ write any 2 names of systems? Answer: Mycin and Dendral R1/Xcon Why GA algorithm gives same solution always reason.3 marks how various parts of truck fit together to form a truck. Backwards chaining detail description 5 marks.defrule clips 2 marks. Monotonic n non monotonic 2 marks --------------How does neural network resemble the human brain? Answer:- (Page 187) It resembles the brain in two respects • Knowledge is acquired by the network through a learning process (called training) • Interneuron connection strengths known as synaptic weights are used to store the knowledge Elaborate the goal state of STRIPS. 2 Answer: Goal is also represented in the same manner as a state. For example, if the goal of a planning problem is to be at the hotel with radio, it is represented as, at(hotel) _ have(radio Write disadvantages of Artificial Neural Networks. 5marks Answer:- (Page 187) • The power of ANNs lie in their parallel architecture – Unfortunately, most machines we have are serial (Von Neumann architecture) • Lack of defined rules to build a neural network for a specific problem – Too many variables, for instance, the learning algorithm, number of neurons per layer, number of layers, data representation etc • Knowledge is implicit • Data dependency Fuzzy logic includes fixes or partially truth. Describe this statement. 3 Fuzzy logic is a superset of conventional (Boolean)logic that has been extended to handle the concept of partial truth -- truth values between "completely true" and "completely false". Increment the combination of has no effect on the instance space, explain? 3 Give 5 names of the parts of Fuzzy Inference system? 5 Answer:- (Page 154) • Fuzzification of the input variables • Application of fuzzy operator in the antecedent (premises) • Implication from antecedent to consequent • Aggregation of consequents across the rules • Defuzzification of output Strategy of Un-supervised..? 5 • Useful for finding patterns in large data sets • Form clusters of input data • Map the clusters into outputs • Given a new example, find its cluster, and generate the associated output 60% mcqs from Moaaz file What is hypothesis space?3 marks The hypothesis space used by a machine learning system is the set of all hypotheses that might possibly be returned by it. It is typically denoted by a hypothesis language, possibly in conjunction with a language bias. What is knowledge acquisition? 2 mrks Knowledge acquisition is the process of extracting, structuring and organizing knowledge from one source, usually human experts What is inductive learning? 2 mrks Answer:- (Page 162) Inductive learning takes examples and generalizes rather than starting with existing knowledge. For example, having seen many cats, all of which have tails, one might conclude that all cats have tails. Among Entropy and information gain which is the best to measure effectiveness? 2 marks Answer:- (Page 177) information gain “Boolean logic is a subset of fuzzy logic.” Do you agree with the statement or not? Give reason to support your answer.(Marks 3) Answer:- (Page 147) Fuzzy logic is a superset of conventional (Boolean) logic that has been extended to handle the concept of partial truth -- truth values between "completely true" and "completely false". For example, There are two persons. Person A is standing on the left of person B. Person A is definitely shorter than person B. But if boolean gauge has only two readings, 1 and 0, then a person can be either all or short. Let‟s say if the cut off point is at 5 feet 10 inches then all the people having a height greater than this limit are taller and the rest are short. Advantage of ANN’s? Excellent for pattern recognition Excellent classifiers Handles noisy data well Good for generalization Elaborate planning. 2marks Answer: Planning is an advanced form problem solving which generates a sequence of operators that guarantee the goal. Furthermore, such sequence of operators or actions (commonly used in planning literature) is called a plan. Robots features?5mrks What is fuzzy logic? A type of logic that recognizes more than simple true and false values. With fuzzy logic, propositions can be represented with degrees of truthfulness and falsehood. For example, the statement, today is sunny,might be 100% true if there are no clouds, 80% true if there are a few clouds, 50% true if it's hazy and 0% true if it rains all day. Fuzzy logic has proved to be particularly useful in expert system and other artificial intelligence applications. Classical logic A classical set is a container, which wholly includes or wholly excludes any given element. What is computer vision? Application area of computer vision? Computer vision extracts useful information from static pictures and sequence of images Steps of Expert System Development Lifecycle? Answer:- (Page 129) • Feasibility study • Rapid prototyping • Alpha system (in-house verification) • Beta system (tested by users) • Maintenance and evolution unsupervised leaning methadlogy? Rep Fuzzy logic and classical difference? Write disadvantages of Artificial Neural Networks. 5marks Answer:- (Page 187) • The power of ANNs lie in their parallel architecture – Unfortunately, most machines we have are serial (Von Neumann architecture) • Lack of defined rules to build a neural network for a specific problem – Too many variables, for instance, the learning algorithm, number of neurons per layer, number of layers, data representation etc • Knowledge is implicit • Data dependency Features of Robot? ► Reasoning, dealing with uncertainty ► Vision, learning ► Autonomy, physical Intelligence 2 Write CLIPS Command for “Remove only Facts ” The retract command is used to remove or retract facts (retract 1)remove fact 1 (retract 13)removes fact 1 and 3 3 Domain expert 4In the Expert system which memory is used and also compare the memory with 5 Quantifiers and ------difference - Differentiate between Mutation and Crossover. (2 Marks) Solution: (Page 81) In Mutation, each “Individual” (or “solution”) has one parent. In Inheritance or Crossover, each “Individual” (or “solution”) has two parents. 5 Genetic algorithm Ans: Knowledge and its types: Durkin refers to it as the understanding of a subject area. A well-focused subject area is referred to as a knowledge domain, for example: Medical domain, Engineering Domain, Business Domain etc. if we analyse the various types of knowledge we using everyday life we can broadly define knowledge to the one of the categories. Procedural Knowledge: It describe how to do things provide a set of direction of how to perform certain tasks, e.g. how to drive a car. Declarative knowledge: It describe object whether then process what is about e, g. it is sunny today. Q) How can you elaborate the "explanation facility" in expert system? Elaborate it with an example. (5 Marks) Ans:Expert system are a popular and useful application area in artificial intelligence. Having studied KRR it is instructive to study expert system to see practical Manifestation of the principal learnt there. The possess specialized knowledge in a certain area. They possess experience in the given area. They can provide upon elicitation and explanation on their decisions. They have a skill set that enables them to translate the specialized knowledge gained through experience into solution. Q) Which components of an Artificial Intelligent System collects information from its environment? Also explain which kind of information it can collect? (3 Marks) Ans: AI system has a perception component that allows a system to get information from its environment. As with human perception this may be visual, audio or other forms of sensory information. The system must then form a meaningful and useful representation of this information internally. Q) Out of human experts and expert system, which one do you think is better in terms of availability? Also explain why. (3 Marks) Ans: Learning ability of human experts is best. Because of its Knowledge and reasoning. Q) Briefly describe the appropriate situation for application of Adversarial Search and Genetic Algorithm. (2 Marks) Ans: If we have a situation analyser that converts all judgement about board situation into a single overall quality number, this situation analyser is also called a static evaluator. Q) Write the command which is used to start execution of a CLIPS program. (2 Marks) Ans: CLIPS> Command can be entered here to leave CLIPS (exit) Give definition of Expert System. Answer: (Page#111) Expert Systems Expert Systems (ES) are a popular and useful application area in AI. Having studied KRR, it is instructive to study ES to see a practical manifestation of the principles learnt there. Question No: 36 In Genetic algorithm if we use only crossover and not mutation then does it make any hurdle in finding our desired solution or not? Give reason to support your answer?(5) Answer: Knowledge and its types Before we go any further, lets try to understand what „knowledge‟ is. Durkin refers to it as the “Understanding of a subject area”. A well-focused subject area is referred to as a knowledge domain, for example, medical domain, engineering domain, business domain, etc.. If we analyze the various types of knowledge we using every day life, we can broadly define knowledge to be one of the following categories: •Procedural knowledge: Describes how to do things, provides a set of directions of how to perform certain tasks, e.g., how to drive a car. •Declarative knowledge: It describes objects, rather than processes. What is known about a situation, e.g. it is sunny today, and cherries are red. The genetic algorithm technology comes from the concept of human evolution. An AI system has a perception component that allows the system to get information from its environment. As with human perception, this may be visual, audio or other forms of sensory information. The system must then form a meaningful and useful representation of this information internally. This knowledge representation maybe static or it may be coupled with a learning component that is adaptive and draws trends from the perceived data. An expert system may take two main roles, relative to the human expert. It may replace the expert or assist the expert This knowledge representation maybe static or it may be coupled with a learning component that is adaptive and draws trends from the perceived data. ----------------- is based on forming, or inducing a „generalization‟ from a limited set of observations ► Inductive reasoning (Page 102) ►Deductive reasoning ► Analogical reasoning ► Common-sense reasoning Question No: 8 (Marks: 1) - Please choose one Hill Climbing is basically a ------------- with a measure of quality that is assigned to each node in the tree. ►Depth First Search (Page 39) ►Breadth First Search ►Best First Search ►Beam Search In Basic Genetic Algorithm the term mutation refers to a small random ________. ►Number ►Change (Page 77) ►Operator ►Operand Question No: 18 ( Marks: 1 ) - Please choose one An expert system may replace the expert or assist the expert. ►True (Page 113) rep ►False Question No: 19 ( Marks: 1 ) - Please choose one Conventional programming focuses on _______, while ES programming focuses on ________ ►Solution, Problem (Page 122) ►Problem, Solution ►Problem, Expert ►Solution, Expert Question No: 20 ( Marks: 1 ) - Please choose one In backward chaining terminology, the hypothesis to prove is called the ________. ►Proof ►Goal (Page 126) ►Plan ►None of the given Question # 1 of 10 ( Marks: 1 ) - Please choose one Some essential components of problem solving are Problem statement, _________, solution space and Operators ►Complex State ►Initial State ►Intermediate State ►Goal State (Page 17) Question # 2 of 10 ( Marks: 1 ) - Please choose one The traveling inside a solution space requires something called as ___________ ►Operands ►Inner solution ►Space solution ►Operators (Page 18) Question # 4 of 10 ( Marks: 1 ) - Please choose one Which of the following disciplines provides us with the theories of structure and meaning of language ►Linguistic (Page 9) ►Philosophy ►Biology ►Psychology Question # 4 of 10 ( Marks: 1 ) - Please choose one An AI system has a ____________ component that allows the system to get information from its environment. ►Planning ►Perception (Page 89) ►Learning ►Execution Question # 6 of 10 ( Marks: 1 ) - Please choose one A statement in conjunctive normal form (CNF) consists of __________ ►ANDs of Ors. (Page 107) ►ANDs ►Ors ►Ors of ANDs Intelligence is the ability to ►Think / learn/Plan/ Schedule (Page 5) ►Recognize / Remember ►Problem Solving ►All of the Above Question # 7 of 10 ( Marks: 1 ) - Please choose one Procedures that search the solution space in an uninformed manner are usually costly with respect to _____. ►Time ►Space ►Time and space both ►All of the given (Page 37) Question # 9 of 10 ( Marks: 1 ) - Please choose one From discipline of _____________ we have the tools and techniques to investigate the human mind and ways to represent the resulting theories ►Computer Science ►Biology ► Mathematics ► Psychology (Page 9) But in reality, exploring the entire search space is never feasible and at times is not even possible How we can elobrate “defrule” in clips? Which is best human expert system and expert system? Learning ability of human expert is best. Q: statment1: ali wear a long shoes DEDUCTIVE Statement 2: it is rainy day Abductive reasoning Statment3: ali wear long shoes in rainy season Abductive reasoning Shallow and structural knowledge? Solution: (Page 90) Heuristic knowledge: Rule-of-thumb, e.g. if I start seeing shops, I am close to the market. 1. Heuristic knowledge is sometimes called shallow knowledge. 2. Heuristic knowledge is empirical as opposed to deterministic Structural knowledge: Describes structures and their relationships. e.g. how the various parts of the car fit together to make a car, or knowledge structures in terms of concepts, sub concepts, and objects. Knowledge representation and preception are closly if yes or not explain it? Solution: (Page 89) An AI system has a perception component that allows the system to get information from its environment. As with human perception, this may be visual, audio or other forms of sensory information. The system must then form a meaningful and useful representation of this information internally. This knowledge representation maybe static or it may be coupled with a learning component that is adaptive and draws trends from the perceived data.