Artificial Intelligence - Unit 1
Unit - 1
Introduction : Introduction to Artificial Intelligence, Foundations and History of AI, Applications of AI, Intelligent Agents, Structure of Intelligent Agents, Computer vision, Natural Language Possessing.
Important Questions :
1. What is Artificial Intelligence ?
- John McCarthy, who coined the term Artificial Intelligence in 1956, defines it as "the science and engineering of making intelligent machines", especially intelligent computer programs.
- Artificial Intelligence (AI) is the intelligence of machines and the branch of computer science that aims to create it.
- Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines
- AI is the study of the mental faculties through the use of computational models. How to make computers fo things which, at the moment, people do better.
- AI is the study and design of intelligent agents, where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success.
2. What is Intelligence ?
Ans. Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines.
- The ability to improve behavior through learning is the hallmark of intelligence, and thus the ultimate challenge of AI and robotics. - Maja J Mataric
- Intelligence include 1. Analytical ability 2. Creative ability 3. Practical ability. Successfully intelligent people are not necessarily high in all three abilities, but find a way effectively to exploit whatever pattern of abilities they may have. - Robert Sternberg.
3. Differentiate between Intelligence and Artificial Intelligence ?
Ans.
4. What is Hard or Strong AI & Weak or Soft AI ?
Ans. Generally, artificial intelligence research aims to create AI that can replicate human intelligence completely.
Strong AI refers to a machine that approaches or supersedes human intelligence,
5. Explain how does Conventional Computing differ from the Intelligence Computing.
Ans.
6. What are the Approaches of AI ?
Ans. The definition of AI gives four possible approaches to pursue :
Fig 3: Basic steps in scene interpretation
Table 1: Difference between Intelligence and AI
- If it can do typically human tasks,
- If it can apply a wide range of background knowledge and
- If it has some degree of self-consciousness.
Strong AI aims to build machines whose overall intellectual ability is indistinguishable from that of a human being.
Weak AI refers to the use of software to study or accomplish specific problem solving or reasoning tasks that so not encompass the full range of human cognitive abilities.
- Example : a chess program such as Deep Blue
- Weak AI does not achieve self-awareness; it demonstrates wide range of human-level cognitive abilities; it is merely an intelligent, a specific problem-solver.
Table 2: Strong AI and Weak AI
Table 3: Conventional Computing and Intelligence Computing
- Systems that think like humans.
- Systems that think rationally.
- Systems that act like humans.
- Systems that act rationally.
Traditionally, all four goals have been followed and the approaches were :
Table 4: Approaches of AI
7. What are the goals of AI ?
Ans. Replicate human intelligence : still a distant goal.
Solve knowledge intensive tasks. Make an intelligent connection between perception and action.
Enhance human-human, human-computer and computer interaction / communication.
- Engineering based AI Goal : Develop concepts, theory and practice of building intelligence machines. Emphasis is on system building.
- Science based AI Goal : Develop concepts, mechanisms and vocabulary to understand biological intelligent behaviour. Emphasis is on understanding behaviour.
8. Explain the 4 approaches of AI.
Ans. The approaches followed are defined by choosing goals of the Computational Model, and basis for evaluating performance of the system.
Cognitive science : Think human-like -
- An exciting new effort to make computers think; that it is, the Machine with minds, in the full and literal sense.
- Focus is not just on behaviour and I/O, but looks at reasoning process.
- Computational model as to how results were obtained.
- Goal is not just to produce human-like behaviour but to produce a sequence of steps of the reasoning process, similar to the steps followed by a human in solving the same task.
Laws of Thought : Think Rationally -
- The study of mental faculties through the use of computational models; that it is, the study of the computational that make it possible to Perceive, reason and act.
- Focus is on inference mechanisms that are provably correct and Guarantee an optimal solution.
- Develop systems of representation to allow inferences to be like "Socrates is a man. All men are mortal. Therefore Socrates is mortal."
- Goal is to formalize the reasoning process as a system of logical rules and procedures for inference.
- The issue is, not all problems can be solved just by reasoning and inferences.
Turing test : Act human-like -
- The art of creating machines that perform functions requiring intelligence when performed by people; that it is the study of, how to make computers do things which at the moment people do better.
- Focus is on action, and not intelligent behaviour centered around representation of the world,
- A Behaviorist approach, is not concerned with how to get results but to the similarity to what human results are.
- Example - Turing test
Rational Agent : Act Rationally -
- Tries to explain and emulates intelligent behaviour in terms of computational processes: that it is concerned with the automation of intelligence.
- Focus is on systems that act sufficiently if not optimally in all situations.
- It is passable to have imperfect reasoning if the job gets done.
- Goal is to develop systems that are rational and sufficient.
9. What is Turing Test ? Explain.
Ans. In 1950, Mind magazine published and article " Can a machine think? " which triggered a controversial topic. Alan Turing proposed and imitation game which was later modified as "Turing Test".
- 3 rooms contain : a person, a computer, and an interrogator.
- The interrogator can communicate with the other 2 by teletype (to avoid the machine imitate the appearance or voice of the person).
- The interrogator tries to determine which is the person and which is the machine.
- The machine tries to fool the interrogator to believe that it is the human, and the person also tries to convince the interrogator that is the human.
- If the machine succeeds in fooling the interrogator, then conclude that the machine is intelligent.
- Goal is to develop systems that are human-like.
Fig 1: Turing Test
10. What are the various Techniques of AI ?
Ans. Various techniques that have evolved, can be applied to a variety of AI tasks.
The techniques are concerned with how we represent, manipulate and reason with knowledge in order to solve problems.
Example -
Techniques, not all "intelligent" but used to behave as intelligent
- Describe and match
- Goal reduction
- Constraint satisfaction
- Tree Searching
- Generate and test
- Rule based systems
Biology-inspired AI techniques are currently popular
- Neural Networks
- Genetic Algorithms
- Reinforcement learning
11. What are the disciplines of AI ?
Ans. The subject of artificial intelligence spans a wide horizon.
It deals with the various kinds of knowledge representation schemes, different techniques of intelligent search, various methods for resolving uncertainty of data and knowledge, different schemes for automated machine learning and many others. Among the application areas of AI, we have Expert systems, Game-laying, and Theorem-proving, Natural language processing, Image recognition, Robotics and many others. The subject of artificial intelligence has been enriched with a wide discipline of knowledge from Philosophy, Psychology, Cognitive Science, Computer Science, Mathematics and Engineering.
Fig 2: Disciplines of AI
12. What is the role of AI in Computer Vision and NLP ?
Ans.
- Image Understanding and Computer Vision : A digital image can be regarded as a two-dimensional array of pixels containing grey levels corresponding to the intensity of the reflected illumination received by a video camera. For interpretation of a scene, its image should be passed through three basic processes : low, medium, and high level vision.
The importance of low level vision is to pre-process the image by filtering from noise. The medium level vision system deals with enhancement of details and segmentation (i.e., partitioning the image into objects of interest). The high level vision system includes three steps : recognition of the objects from the segmented image, labeling of the image and interpretation of the scene. Most of the AI tools and techniques are required in high level vision systems. Recognition of objects from its image can be carried out through a process of pattern classification, which at present is realized by supervised learning algorithms. The interpretation process, on the other hand, requires knowledge-based computation.
- Speech and Natural Language Understanding : Understanding of speech and natural languages is basically two classical problems. In speech analysis, the main problem is to separate the symbols of a spoken word and determine features like amplitude, and fundamental and harmonic frequencies of each symbol. The words then could be identified from the extracted features by pattern classification techniques. Recently, artificial neural networks have been employed to classify words from their features. The problem of understanding natural languages like English, on the other hand, includes syntactic and semantic interpretation of the words in a sentence, and sentences in a paragraph. The syntactic steps are required to analyse the sentences by its grammar and are similar with the steps of compilation. The semantic analysis, which is performed following the syntactic analysis, determines the meaning of the sentences from the association of the words and that of a paragraph from the closeness of the sentences. A robot is capable of understanding speech in a natural language will be of immense importance, for it could execute any task verbally communicated to it. The phonetic typewriter, which prints the words pronounced by a person, is another recent invention where speech understanding is employed in a commercial application.
13. What can AI systems do and can't do ?
Ans. Today's AI systems have been able to achieve limited success in some of these tasks.
Ans. Today's AI systems have been able to achieve limited success in some of these tasks.
- In Computer vision, the systems are capable of face recognition.
- In Robotics, we have been able to make vehicles that are mostly autonomous.
- In Natural language processing, we have systems that are capable of simple machine translation.
- Today's Expert systems can carry out medical diagnosis in a narrow domain.
- Speech understanding systems are capable of recognizing several thousand words continuous speech
- Planning and scheduling systems had been employed in scheduling experiment with the Hubble telescope.
- The Learning systems are capable of doing text categorizing into about a 1000 topics.
- In Games, AI systems can play at the Grand Master level in chess (World champion), checkers, etc.
What can AI systems NOT do yet ?
- Understand natural language robustly (e.g., read and understand articles in a newspaper).
- Surf the web.
- Interpret an arbitrary visual scene.
- Learn a natural language.
- Construct plans in dynamic real-time domains.
- Exhibit true autonomy and intelligence.
14. Name few famous AI systems developed ?
Ans.
a) ALVINN : Autonomous Land Vehicle In a Natural Network
In 1989, Dean Pomerleau at CMU created ALVINN. This is a system which learns to control vehicles by watching a person drive. It contains a neural network whose input is a 30*32 unit two dimensional camera image. The output layer is a representation of the direction the vehicle should travel.
The system drove a car from the East Coast of USA to the west coast, a total of 2850 miles. Out of this about 50 miles were driven by a human, and the rest solely by the system.
b) Deep Blue :
In 1997, the Deep Blue chess program created by IBM, beat the current world chess champion, Gary Kasparov.
c) Machine translation :
A system capable of translation between people speaking different languages will be a remarkable achievement of enormous economic and cultural benefit. Machine translation is one of the important fields of endeavour in AI. While some translating systems have been developed, there is a lot of scope for improvement in translation quality.
d) Autonomous agents :
In space exploration, robotic space probes autonomously monitor their surroundings, make decision and act to achieve their goals.
NASA's Mars rovers successfully completed their primary three-month mission in April, 2004. The Spirit rover had been exploring a range of Martians hills that took two months to reach. It is finding curiously eroded rocks that may be new pieces to the puzzle of the region's past. Spirit's twin, Opportunity, had been examining exposed rock layers inside a crater.
e) Internet agents :
The explosive growth of the internet has also led to growing interest in internet agents to monitor user's tasks, seek needed information, and to learn which information is most useful.
15. What is an Agent ?
Ans. An agent acts in an environment. An agent perceives its environment through sensors. The complete set of inputs at a given time is called a percept. The current percept, or a sequence of percepts can influence the actions of an agent. The agent can change the environment through actuators or effectors. An operation involving an effector is called an action. Actions can be grouped into action sequences. The agent can have mapping from percepts sequences to actions.
A performance measures has to be used in order to evaluate an agent.
An autonomous agent decides autonomously which action to take in the current situation to maximize progress towards its goals.
Fig 4: Diagram of an Agent
16. What is PEAS & Give some examples ?
Ans.
- Performance measure,
- Environment,
- Actuators,
- Sensors
In designing an agent, the first step must always be to specify the task environment (PEAS) as fully as possible
PEAS for an automated taxi driver
- Performance measure : Safe, fast, legal, comfortable trip, maximize profits.
- Environment: Roads, other traffic, pedestrians, customers.
- Actuators: Steering wheel, accelerator, brake, signal, horn.
- Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard.
PEAS for a medical diagnosis system
- Performance measure: Healthy patient, minimize costs, lawsuits.
- Environment: Patient, hospital, staff.
- Actuators: Screen display (questions, tests, diagnoses, treatment, referrals)
- Sensors: Keyboard (entry of symptoms, findings, patient's answers)
PEAS for a satellite image analysis system
- Performance measure: Correct image categorization
- Environment: Down link from orbiting satellite
- Actuators: Display categorizing of scene
- Sensors; Color pixel arrays
PEAS for a part-picking robot
- Performance measure: Percentage of parts in correct bins
- Environment: Conveyor belt with parts, bins
- Actuators: Jointed arm and hand
- Sensors: Camera, joint angle sensors
17. What are the various environment types?
Ans.
Fully observable vs. partially observable :
- An environment is fully observable if an agent's sensors give it access to the complete state of the environment at each point in time.
- Fully observable environment are convenient, because the agent need not maintain any internal state to keep track of the world.
- An environment might be partially observable because of noisy and inaccurate sensors of because parts of the state are simply missing from the sensor data.
- Example- vacuum cleaner with local dirt sensor, taxi driver.
Deterministic vs. stochastic :
- The environment is deterministic if the next state of the environment is completely determined by the current state and the action executed by the agent.
- In principle, an agent need not worry about uncertainty in a fully observable, deterministic environment.
- If the environment is partially observable then it could appear to be stochastic.
- Examples: Vacuum world is deterministic while taxi driver is not.
- If the environment is deterministic except for the actions of other agents, then the environment is strategic.
Episodic vs. sequential :
- In episodic environments, the agent's experience is divided into atomic "episodes" (each episode consists of the agent perceiving and then performing a single action), and the choice of action in each episode depends only on the episode itself.
- Examples: classification tasks.
- In sequential environments, the current decision could affect all future decisions.
- Examples: chess and taxi driver.
Static vs. dynamic :
- The environment is unchanged while an agent id deliberating.
- Static environments are easy to deal with because the agent need not keep looking at the world while it is deciding on the action or need it worry about the passage of time.
- Dynamic environments continuously ask the agent what it wants to do.
- The environment id semi-dynamic if the environment itself does not change with the passage of time but the agent's performance score does.
- Examples: taxi driving is dynamic, chess when played with a clock is semi-dynamic, crossword puzzles are static.
Discrete vs. continuous :
- A limited number of distinct, clearly defined states, percepts and actions.
- Examples: Chess has finite number of discrete states, and has discrete set of percepts and actions. Taxi driving has continuous states, and actions.
Single-agent vs. multi-agent :
- An agent operating by itself in an environment is single agent.
- Examples: Crossword is a dingle agent while chess is two-agents.
- Questions: Does an agent A have to treat an object B as an agent or can it be treated as a stochastically behaving object.
- Whether B's behaviour is best described by as maximizing a performance measure whose value depends on agent's A behaviour.
- Examples: Chess is a competitive multi-agent environment while taxi driving is a partially cooperative multi-agent environment.
18. What are the various types of Agents ?
Ans.
Simple reflex agents :
- Select actions on the basis of the current percept ignoring the rest of the percept history
- Example: simple reflex vacuum cleaner agent
- Condition-action-rule
- Example: i f car-in-front-is-breaking then initiate braking
Fig 5: Simplex reflex agent
- Simple reflex agents are simple, but they turn out to be of very limited intelligence
- The agent will work only if the correct decision can be made on the basis of the current percept-that is only if the environment if fully observable.
- Infinite loops are often unavoidable - escape could be possible by randomizing
Model Based Agents :
- The agent should track of the part of the world it can't see now
- The agent should maintain some sort of internal state that depends on the percept history and reflects at least some of the unobserved aspects of the current state.
- Updating the internal state information as time goes by requires two kinds of knowledge to be encoded in the agent program. 1) Information about how the world evolves independently of the agent. 2) Information about how the agent's own actions affects the world.
- Model of the world - model based agents.
Fig 6: Model based agents
Goal Based Agent :
- Knowing about the current state of the environments not always enough to decide what to do (e.g., decision at a road junction).
- The agent needs some sort of goal information that describes situations that are desirable.
- The agent program can combine this with information about the results of possible actions in-order to choose actions that achieve the goal.
- Usually requires search and planning
Fig 7: Goal Based Agent
Utility Based Agent :
- Goals alone are not really enough to generate high-quality behaviour in most environments - they just provide a binary distinction between happy and unhappy states.
- A more general performance measure should allow a comparison of different world states according to exactly how happy they would make the agent if they could be achieved
- Happy - Utility (the quality of being useful)
- A utility function maps a state onto a real number which describes the associated degree of happiness
Fig 8: Utility based agent
19. What is a Learning Agent ?
Ans.
- Learning element - responsible for making improvements
- Performance element - responsible for selecting external actions
- Learning element used feedback from the critic on how the agent is doing and determines how the performance element should be modified to do better in the future.
- Problem generator is responsible for suggesting actions that will lead to a new and informative experiences.
Fig 9: Learning Agent
20. What is a rational agent ?
Ans. It always select an action based on the percept sequence it has received so as to maximize its performance measure given the percepts it has received and the knowledge possessed by it.
21. What is a bounded rational agent ?
Ans. A rational agent that can use only bounded resources cannot exhibit the optimal behaviour. A bounded rational agent does the best possible job of selecting goof actions given its goal, and given its bounded resources.
22. What is and autonomous agent ?
Ans. Autonomous agents are software entities that are capable of independent action in dynamic, unpredictable environment. An autonomous agent can learn and adapt to a new environment.
Reference -
Siasabita mam (Krishna engg. college - Asst. professor)
Loveleen Gaur
Wikipedia
****ATCAPH.com****
Comments
Post a Comment