CSCI 4410

1. CSCI 4410 Introduction to Artificial Intelligence

2. What is AI? • Difficult to define • “The Intelligence of a System is inversely proportional to our understanding of it”

3. What is AI? • making computer programs that appear to think? • the automation of activities we associate with human thinking, like decision making, learning ? • the art of creating machines that perform functions that require intelligence when performed by people ? • the study of mental faculties through the use of computational models ? • the study of computations that make it possible to perceive, reason and act ? • a branch of computer science that is concerned with the automation of intelligent behavior ? • anything in Computing Science that we don't yet know how to do properly ?

4. AI • “The art of creating machines that perform functions that require intelligence when performed by people.” (Kurzweil) • “The study of how to make computers do things at which, at the moment, people are better.” (Rich and Knight) • But what about creativity? • Many would argue machines are already writing rap music and reality shows

5. Rational Systems • How do we know how humans think? • Introspection vs. psychological experiments • Brain research (scanning, experiments, testing) • Cognitive Science

6. Rational Systems • Humans are not always ‘rational’ • Rational - defined in terms of logic? • Logic can’t express everything (e.g. uncertainty) • Logical approach is often not feasible in terms of computation time - needs ‘guidance’ • We will never get to intelligence with rules

7. Satisfiability • Rule systems must be checked • This is the Satisfiability Problem • NP-complete • Checking all the states of a large rule system is computationally expensive

8. Turing Test • Described by Alan Turing in 1950 • A human judge engages in a natural language conversation with a human and a machine • If the judge cannot reliably tell which is which, then the machine passes the Turing test. • The conversation is usually limited to text.

9. Turing Test • However…

10. Turing Test • A machine passing the Turing test may be able to simulate human conversation • Is this intelligence? • how do we know humans don't just follow rules? • Blockhead – all paths • Chinese room - rules • Can young children pass the test?

11. Turing Test • Turing test measures human-like behavior • Even if the Turing test is a good definition of intelligence, it may not indicate consciousness. • Does intelligence imply consciousness?

12. Practical AI • Do we care whether a system: • Replicates human thought processes • Makes the same decisions as humans • Uses purely logical reasoning

13. AI in Practice • Medical advice system • Part-picking robots • Credit card fraud detection • Spam filters • Medical diagnosis, teleoperated/micro surgery

14. AI in Practice • Information retrieval, Google • Scheduling, logistics, supply chain management • Aircraft and pipeline inspection • Speech recognition, generation, translation

15. AI in Practice • And robots and chatbots

16. Heuristics • Two fundamental goals: • finding algorithms with good run times and • optimal solutions. • But… these goals are often mutually exclusive • A heuristic is an algorithm that relaxes one or both of these goals

17. Heuristics • Special instances of the problem may cause the heuristic to produce poor results or run slowly • These instances may be rare • Ex: sorting algorithms where the list is already sorted • Matching the heuristic to the domain is important • Heuristics are very common in real world implementations.

18. Example – Spam Assassin • Spam Assassin • uses a wide variety of heuristic rules to determine whether an email is a spam or ham • Bayesian filter • Blacklisting • Regular expression matching

19. Modern Focus Artificial intelligence can be considered under a number of headings: • Search • Representing Knowledge and Reasoning • Planning • Uncertainty • Learning • Interacting with the Environment (e.g. Vision, Speech, Robotics)

20. Search • 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. • Desire for optimal solutions leads to heuristics

21. Knowledge Representation and Reasoning • If we are going to act rationally in our environment, then we must have some way of describing that environment. • how do we represent what we know about the world ? • how do we represent it concisely ? • how do we represent 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 ?

22. Planning 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?

23. Uncertainty Given the set of “uncertain” information, how can we achieve the goals (and how certain are we of that answer). • How do we deal with uncertainty in our daily lives? • How can we make this more systematic • How can we build systems that deal with uncertainty • How can we insure that the systems are reasonable and correct

24. Learning • If a system is going to act truly appropriately, then it must be able to change its actions in the light of experience: • Generating new facts from old • How do we generate new concepts ? • How do we learn to distinguish different situations in new environments ?

25. Knowledge • Virtually all techniques benefit from ‘common sense’ • CYC – a very large database of general purpose knowledge

26. Resolving Ambiguity – Ex. • Consider the following pair of sentences: • Fred saw the plane flying over Zurich. • Fred saw the mountains flying over Zurich. • Humans recognize that in the first sentence, "flying" refers to the plane • In the second sentence, "flying" almost certainly refers to Fred. • Traditional Natural Language systems will have difficulty resolving this syntactic ambiguity • Cyc knows that planes fly and mountains do not, and can reject nonsensical interpretations.