Presentation is loading. Please wait.

Presentation is loading. Please wait.

Artificial Intelligence Mr. Sciame Section 2

Similar presentations


Presentation on theme: "Artificial Intelligence Mr. Sciame Section 2"— Presentation transcript:

1 Artificial Intelligence Mr. Sciame Section 2
The Foundations of AI Artificial Intelligence Mr. Sciame Section 2

2 First Foundation

3 Philosophy (428 BC – Present)
Questions for AI Can formal rules be used to draw valid conclusions? How does the mental mind arise from a physical brain? Where does knowledge come from? How does knowledge lead to action?

4 Applying Rational Thought to Machines
Aristotle – Formulated Logic Da Vinci – Designed the first calculator Wilhelm Schickard – 1st Calculating machine (1623) Blaise Pascal – The Pascal Adder (1642) – The more famous calculating machine; much like an odometer on a car.

5 Pascal and His Adder

6 The Mind as a Physical System
René Descartes ( ) was first to clearly discuss the distinction between mind and matter. A physical mind leaves no room for free will. If the mind was governed by physical laws, it has the free will of a rock “deciding” to fall to Earth.

7 Dualism Descartes proposed dualism
There is a part of the human mind (soul or spirit) outside of nature. This part was exempt from physical laws. He felt animals did not possess this dual nature and could be treated as machines.

8 Materialism Alternative to dualism
The brain’s operation according to the laws of physics constitutes the mind. Free will is the perception of available choices in the choice process.

9 Establishing the Source of Knowledge
Empiricism Nothing is in the understanding, which is not first in the senses. – John Locke Induction General rules are acquired by exposure to repeated associations between their elements. Logical Positivism Knowledge can be characterized by logical theories connected to observational sentences that correspond to sensory inputs

10 Connection of Knowledge to Action
A vital question for AI, since intelligence requires actions as well as reasoning. There must be an understanding of how actions are justifiable (or rational).

11 Aristotle We deliberate not about ends, but about means.

12 Second Foundation

13 Mathematics (800 AD – Present)
Questions for AI What are the formal rules to draw valid conclusions? What can be compared? How do we reason with uncertain information? Three contributions Logic Computation Probability

14 The Formal Rules George Boole (1847) Gottlob Frege (1848-1925)
Boolean Logic Gottlob Frege ( ) Extended Boolean logic to include objects and relations, used today as a basic knowledge representation system. Alfred Tarski ( ) His theory showed how to relate objects in a logic to objects in the real world.

15 The Limits of Logic and Computation
Algorithms Step by step methods for problem solving. The incompleteness theorem Some Functions cannot be represented by algorithms. The Turing Machine (1936 – Alan Turing) You could create a machine capable of computing a computable function No machine can tell in general whether a given program will return an answer, or run forever.

16 Probability The possible outcomes of gambling events

17 THIRD Foundation

18 Economics (1776 to Present)
Questions for AI: How should we make decisions as to maximize payoff? How should we do this when others may not go along? How should we do this when the payoff may be far into the future?

19 Historical Adam Smith (1776) – An Inquiry into the Causes of the Wealth of Nations. First time Economics is treated as a science. The study of making choices that lead to preferred outcomes. Theory updated by John von Neumann (1944) The Theory of Games and Economic Behavior.

20 Decision Theory The Decision Theory: Combines Probability with Utility
Provides a framework for decisions This works for large economies (it doesn’t matter what the other guy does); smaller ones treat this as a game (the actions of one affect others)

21 Payoff for the Future Herbert Simon (1978) Won the Nobel Prize
Showed that making decisions that were “good enough,” rather than looking for an optimal decision, gave a better description of human behavior.

22 FOURTH Foundation

23 Neuroscience (1861 to Present)
Questions for AI: How do brains process information?

24 Definition Neuroscience is the study of the nervous system, and in particular, the brain.

25 The Neuron Parts include: Cell Body Dendrites Axon

26 Comparason Computer Human Brain Computational Units 1 CPU, 108 gates
1011 neurons Storage Units 1010 bits RAM 1011 bits disk 1014 synapses Cycle Time 10-9 seconds 10-3 seconds Bandwidth 1010 bits/second 1014 bits/second Memory Updates/Second 109 1014

27 FIFTH Foundation

28 Psychology (1879 to Present)
Questions for AI: How do humans and animals think and act?

29 Studies Behavioralism Cognitive Psychology Cognitive Science

30 Behaviorism The study of animal behavior
Relationship of stimuli to responses

31 Cognitive Psychology The view of the brain as an information processing device. Three steps of a knowledge based agent: The stimulus must be turned into an internal representation The representation is changed by cognitive processes into new internal representations These are translated back into actions.

32 Cognitive Science Addresses the psychology of memory, language, and logical thinking “A cognitive theory should be like a computer program” (Anderson, 1980) AI Examples: Newell and Simon’s The Logical Thinking Machine Noah Chomsky and language

33 SIXTH Foundation

34 Computer Engineering (1940 to Present)
Questions for AI: How can we build an efficient computer? We discussed this in our first notes.

35 SEVENTH Foundation

36 Control Theory and Cybernetics (1948 to Present)
Questions for AI: How can artifacts operate under their own control?

37 Inventions of Control Devices
250 BC – Water Clock 1600’s – Thermostat (Drebbel) 1800’s – Steam Engine (James Watt)

38 Theories Control Theory: Objective Function
A regulatory mechanism trying to minimize “error” (the difference between the current state and the goal state) Objective Function Designing systems that behave optimally.

39 EIGHTH Foundation

40 Linguistics (1957 to Present)
Questions for AI: How does language relate to thought?

41 Books on the Subject Verbal Behavior – B.F. Skinner
Syntactic Structures – Noah Chomsky Skinner: Behaviorialist Approach Chomsky: Creativity in language Children’s sentences.

42 Natural Language Processing
Understanding Language: Not just sentence structure. Also subject matter and context


Download ppt "Artificial Intelligence Mr. Sciame Section 2"

Similar presentations


Ads by Google