ARTIFICIAL INTELLIGENCE : OVERVIEW 1 DEFINATIONS:
1. AI IS THE BRANCH OF COMPUTER SCIENCE THAT IS CONCERNED WITH THE AUTOMATION OF INTELLIGENT BEHAVIOR. 2. AI IS STUDY OF HOW TO MAKE COMPUTERS DO THINGS WHICH AT THE MOMENT, PEOPLE DO BETTER. 3. AI is Building intelligent entities. 4. AI is the science of automating intelligent behaviors currently achievable by humans only. 5. AI is Getting computers to do tasks which require human intelligence.
Biomedical Department, NIT Raipur
10/10/09
What is Intelligence 2
Intelligence is the ability to form plans to achieve goals by interacting
with an information-rich environment. Intelligence encompasses abilities such as:
understanding language perception learning Reasoning Making conclusions
Biomedical Department, NIT Raipur
10/10/09
Philosophical Issues 3
What is intelligence? Can a machine be truly “intelligent”? Is there more to
human intelligence than rules, data and calculations? Test: Turing Test: Can someone tell which is the machine, when communicating to human and to a machine in another room? If not, can we call the machine intelligent?
Biomedical Department, NIT Raipur
10/10/09
Turing test AI system
Experimenter
Control
Biomedical Department, NIT Raipur
4
10/10/09
WHY AI?? 5
Two main goals of AI:
To understand human intelligence better. We test theories of human intelligence by writing programs which emulate it.
To create useful “smart” programs able to do tasks that would normally require a human expert.
Biomedical Department, NIT Raipur
10/10/09
TASK DOMAINS OF ARTIFICIAL INTELLIGENCE 6
MUNDANE TASKS: 1. Perception: Vision & speech. 2. Natural Language: Understanding, Generation, & Translation. 3. Commonsense reasoning. 4. Robot control.
Biomedical Department, NIT Raipur
10/10/09
TASK DOMAINS OF ARTIFICIAL INTELLIGENCE 7
FORMAL TASKS: 1. Games: Chess, Checkers etc. 2. Mathematics: Geometry, Logic, Integral Calculus, Proving properties. EXPERT TASKS : 1. Engineering: Design, Fault finding, Manufacturing. 2. Scientific Analysis. 3. Medical Diagonosis. 4. Financial Analysis. Biomedical Department, NIT Raipur
10/10/09
Who does AI? 8
Many disciplines contribute to goal of
creating/modelling intelligent entities:
Computer Science Psychology (human reasoning) Philosophy (nature of belief, rationality, etc) Linguistics (structure and meaning of language) Human Biology (how brain works)
Subject draws on ideas from each discipline.
Biomedical Department, NIT Raipur
10/10/09
The Main Topics in AI 9
Artificial intelligence can be considered under a number of headings: Search Representing knowledge and reasoning with it Planning Learning Interacting with the environment (e.G. Vision, speech, robotics)
Biomedical Department, NIT Raipur
10/10/09
SEARCH 10 Search is the fundamental technique of AI.
Possible answers, decisions or courses of action are structured into an abstract space, which we then search.
Search is either "blind" or "informed":
Blind.
We move through the space without worrying about what is coming next, but recognising the answer if we see it.
Informed.
We guess what is ahead, and use that information to decide where to look next.
We may want to search for the first answer that satisfies our goal, or we may want to
keep searching until we find the best answer.
Biomedical Department, NIT Raipur
10/10/09
Knowledge Representation and Reasoning 11
The second most important concept in AI. If we are going to act rationally in our environment, then we
must have some way of describing that environment.
How do we describe what we know about the world ?
How do we describe it concisely ?
How do we describe it so that we can get hold of the right piece of knowledge when we need it ?
How do we generate new pieces of knowledge ?
How do we deal with uncertain knowledge ?
Biomedical Department, NIT Raipur
10/10/09
12
Intelligence Requires Knowledge:
Properties It is voluminous It is hard to characterize accurately It is changing constantly It differs from data by being organized in a way that corresponds to the ways it will be used
Biomedical Department, NIT Raipur
10/10/09
Planning 13
Given a set of goals, construct a sequence of actions that achieves those goals: Often very large search space But most parts of the world are independent of most other parts Often start with goals and connect them to actions No necessary connection between order of planning and order of execution What happens if the world changes as we execute the plan and/or our actions don’t produce the expected results?
Biomedical Department, NIT Raipur
10/10/09
Learning 14
If a system is going to act truly appropriately, then it
must be able to change its actions in the light of experience: How do we generate new facts from old ? How do we generate new concepts ? How do we learn to distinguish different situations in new environments ?
Biomedical Department, NIT Raipur
10/10/09
Interacting With the Environment 15
In order to enable intelligent behaviour, we will have to
interact with our environment. Properly intelligent systems may be expected to: Accept sensory input. Vision, sound, … Interact with humans. Understand language, recognise speech, generate text, speech and graphics, … Modify the environment. Robotics.
Biomedical Department, NIT Raipur
10/10/09