!
CMP2020M
ARTIFICIAL INTELLIGENCE
Marc Hanheide, Patrick Dickinson, Bashir Al-Diri
!
CMP2020M ARTIFICIAL INTELLIGENCE
‣ Lectures
‣ Fridays 11:00 – 12:00, starting today, MB0603
‣ Marc Hanheide (module coordinator), Patrick Dickinson, Bashir Al-Diri
‣ Workshops
‣ Tuesdays 9:00-11:00, starting coming week, CompLab B
‣ Tuesdays 14:00-16:00, starting coming week, CompLab A
‣ Thursday 16:00-18:00, starting coming week, CompLab B
‣ Sinjun Strydom, Ashley Williamson, Peter Lightbody, Joao Santos, Christian Dondrup
‣ Assessment
‣ Component 1: Programming (40%) ‣ Component 2: Examination (60%)
WHAT IS AI?
Thinking humanly
Thinking rationally
Acting humanly
Acting rationally
!
WHAT IS AI?
!
NATURAL VS. ARTIFICIAL INTELLIGENCE THE TURING TEST (1950)
‣ Turing (1950) “Computing machinery and intelligence”:
‣ “Can machines think?” → “Can machines behave intelligently?”
‣ Operational test for intelligent behaviour: the Imitation Game
IS THIS AI?
IS THIS AI?
IS THIS AI?
IS THIS AI?
IS THIS AI?
IS THIS AI?
IS THIS AI?
NAVIGATION IS HARD!
Going from “Home” Night Club to Charlesworth House:
•at least 10 junctions
•assume each junction has 3 options •there are 3^10=59049 possible options!
•How do we do it?
•How do Google,TomTom, etc. do it?
IS THIS AI?
IOS 9 SIRI MEETS IOS 8 SIRI!
CHATBOTS
Human: WhatshallIdo?
Eliza:That’s quite interesting.
Human: What?
Eliza:What do you think ?
Human: I think I should work harder for my course Eliza: Is it important to you that you have your course ? Human: Well,kindof
Eliza: Lets discuss further why your course. Human: I’m interested in it
Eliza: How long have you been interested in it ? Human: since I was a child
Eliza:Were you really ?
Human: yes
Eliza:You seem to be quite positive. Human: I usually am
!
http://nlp-addiction.com/eliza/
‣ ELIZA was the first chatbot
‣ made by Joseph Weizenbaum between 1964 and 1966
‣ very limited knowledge base
‣ operated most by string substitutions
IS THIS AI? http://lcas.lincoln.ac.uk/linda/linda.html
AI is everywhere today!
but the fundamentals haven’t changed too much since the 1950s
!
BIRTH OF AI
‣ The Dartmouth Conference (1956) brought together many of the leading researchers in a variety of topics:
‣ complexity theory
‣ language simulation
‣ neuron nets
‣ abstraction of content from sensory inputs
‣ relationship of randomness to creative thinking ‣ learning machines
“It is the science and engineering of making intelligent machines, especially intelligent computer programs.
It is related to the similar task of
using computers to understand human intelligence, but AI does not have to confine itself to methods
that are biologically observable.”
John McCarthy http://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist)
programs which solve
hard problems*
* where hard has a specific technical
meaning, but is often taken to mean: hard for humans to do, hard for humans to explain how they do it, or hard for a computer to do in a reasonable time, or hard for a reasonable computer to do in a reasonable time
WHERE DO WE STAND TODAY?
“Well, there are two ways of looking at things. You can either look at it from the point of view of biology, or from the point of view of computer science. From the point of view of biology, you could try to imitate the nervous system insofar as you understood the nervous system, or you could try to imitate human psychology insofar as you understand human psychology. The computer-science way of looking at it says that we look at the world and we try to see what problems it presents in order to achieve goals and think about the world rather than about the biology per se. And I would say that the computer-science approach is the one that so far has had the most success.”
John McCarthy
!
ARTIFICIAL INTELLIGENCE SUBFIELDS
‣ Reasoning
‣ Decision making
‣ Planning
‣ (Machine) Learning ‣ Perception
‣ Action
‣ Communication
‣ Common sense
AI is everywhere today!
but the fundamentals haven’t changed too much since the 1950s
You’ll learn the fundamentals… … and how they are employed in today’s world
!
DIFFERENT TAKES ON AI
‣ Major ones covered in CMP2020M: ‣ Symbolic Approaches
‣ Search & Planning
‣ Probabilistic Approaches ‣ beyond “pure” AI
‣ Machine Learning
!
SYMBOLS
‣ A symbol is a name or sign which acts as a substitute for something else
‣ Concepts
‣ Objects
‣ Properties of objects
‣ Relationship between objects
‣ Symbol processing involves manipulation by a machine of information and knowledge represented as symbols to produce new symbols
!
FACTS AND RULES
‣ Fact
‣ X (“I work hard”)
‣ Rule
‣ X →Y (“If I work hard then I will pass my AI exam”)
‣ Inference ‣ Given:
‣ Fact: X
‣ Rule: X → Y ‣ Infer
‣ New fact:Y (“I will pass my AI exam”)
!
DIFFERENT TAKES ON AI
‣ Major ones covered in CMP2020M: ‣ Symbolic Approaches
‣ Search & Planning
‣ Probabilistic Approaches ‣ beyond “pure” AI
‣ Machine Learning
!
SEARCH
!
DIFFERENT TAKES ON AI
‣ Major ones covered in CMP2020M: ‣ Symbolic Approaches
‣ Search & Planning
‣ Probabilistic Approaches
‣ beyond “pure” AI ‣ Machine Learning
!
“UNCERTAIN” SYMBOLS: PROBABILISTIC AI
‣ We write probability(A), or usually P(A) for short, to mean the “probability of A.”
‣ But what does P(A) mean?
‣ P(Iwilldrawaceofhearts)?
‣ P(thecoinwillcomeupheads)? ‣ P(itwillsnowtomorrow)?
!
DIFFERENT TAKES ON AI
‣ Major ones covered in CMP2020M: ‣ Symbolic Approaches
‣ Search & Planning
‣ Probabilistic Approaches
‣ beyond “pure” AI
Machine Learning
‣
MACHINE LEARNING
‣ Systems that can learn from data (rather than manually entered)
‣ System that are trained on (known) data… ‣ … then approximate for new incoming data
!
ONGOING DEBATES
‣ “Strong” AI vs “weak” AI
(or “artificial general intelligence” vs “applied AI”)
‣ BBC debates: http://bcove.me/ lx1vix8x
‣ The actual open letter: http:// futureoflife.org/misc/open_letter
!
COMING…
Date of Lecture
Week
Topic
Lecturer for Friday Lecture
22/01/2016
1
Introduction
Marc Hanheide
29/01/2016
2
Knowledge Representations
Marc Hanheide
05/02/2016
3
Planning I
Marc Hanheide
12/02/2016
4
Planning II
Marc Hanheide
19/02/2016
5
Logic Programming
Bashir Al-Diri
26/02/2016
6
Logic Programming
Bashir Al-Diri
04/03/2016
7
Logic Programming
Bashir Al-Diri
11/03/2016
8
Games AI & Search
Patrick Dickinson
18/03/2016
9
Games AI & Search
Patrick Dickinson
25/03/2016
01/04/2016
08/04/2016
10
Games AI & Search
Patrick Dickinson
15/04/2016
11
Probabilistic AI
Christian Dondrup
22/04/2016
12
Probabilistic AI
Christian Dondrup
29/04/2016
13
Mock Exam
!
!
READING LIST http://lists.library.lincoln.ac.uk/lists/3303ED19-0D88-6DE5-C8C7-03EE24EC6776.html
read chapter 1 (online)