Samenvatting
Summary for Midterm Exam of Introduction to AI
- Instelling
- Tilburg University (UVT)
a detailed, well organized summary for midterm exam, see details in preview.
[Meer zien]Voorbeeld 3 van de 18 pagina's
Voorbeeld 3 van de 18 pagina's
In winkelwagengesponsord bericht van onze partner
Verkoper
Volgen
Voorbeeld van de inhoud
What is AIAI Research Field 1. computer science => programming languages, algorithms, etc.
Collabora ve/ 2. linguis cs => grammar, sound, words, used in communica on
Mul disciplinary/ 3. psychology => mental processes and human behavior
interdisciplinary 4. neuroscience => structure and chemistry of the nervous system
5. philosophy => fundamental ques ons of knowledge, reality, and existence
6. sta s cs
7. robo cs
Cogni ve Science + KEY: views the mind as a symbol manipula ng machine
+ Rela on with AI: both concerned with modeling human behavior and cogni on
GOAL: + understand brain processes as computa onal systems
+ store symbolic representa ons, manipulate via syntac c opera ons
+ human mind as complex system receive, store, retrieve, transform and transmit info
6 Big Ques ons Can we build machines that think, learn, more intelligent, crea ve, have emo ons and are conscious?
+ AI progress has been much slower than expected, full AI is easy to convince/scare people.
Fragmenta on of
AI Research
Ar ficial non-biological. Here, it’s all about the kind of stuff we use to build an agent.
constructed by humans. it’s all about the origin of the agent, and who designed and build it.
Intelligence “Few concepts in psychology have received more devoted a en on and few have resisted
classifica on so thoroughly” -A. S. Reber
“Intelligence is the computa onal part of the ability to achieve goals in the world.
Varying kinds and degrees of intelligence occur in people, many animals and some machines”
-John McCarthy
, Goals of AI
What is AI
John McCarthy “the science and engineering of making intelligent machines”
Marvin Minsky (1968) “the science of making machines do things that would require intelligence if done by men”
John Haugeland (1985) “the exci ng new effort to make computer think … machine with mind, in the full and literal sense”
Ray Kurzweil (1990) “the art of crea ng machines that perform func ons that require intelligence when performed by people”
Accurate statements + making machines do things that would require intelligence if done by people
+ making computers that solve problems in the best possible way
+ making computers that can learn and think for themselves
=> designing computers that solve new problems (less accurate)
=> Strong AI + Understand human mind/brain as a computa onal device, we can build a thought, emo ons, just as
human machine (NOT ONLY detect and imitate),
specific in human mind/brain, general in human can solve wide range problem
Science + Reverse-engineer the mind/brain (modeling human intelligence)
+ object is what IS in human nature, are human machine, can detect and imitate emo on
+ could fail, example: cogni ve psychology, neuroscience, machine learning
Ar ficial General + view intelligent systems as whole
Intelligence + set human-level performance as the only goal, leave alone the other
+ integrate AI’s sub-fields early
=> Weak AI + Machinery not like human but solve problem, interest in tricky problem NOT in human nature,
general in any kind of problem/technique might be entertained, specific in consider a single, isolate
problem)
Engineering + engineer clever machine, object is unknown or to be discovered, INDEPENDENT of human nature
+ already succeeded, example: autonomous cars, recommender systems, speech recogni on so ware
Narrow AI + breaking the big problems down to smaller ones,
+ seek incremental improvement
+ each sub-fields solve its own problem, solving an isolated problem independent of human nature
Four Defini ons of AI
=> Ra onal AI + thinking humanly: study of cogni ve mechanisms such as neural networks simulate human brain
+ Allen Newell and Herbert Simon developed GPS (“General Problem Solver”) in 1961,
+ Ac ng Humanly: machine behaves like human, speak or act like human
Turing Test + capabili es: natural language processing, knowledge representa on, automated reasoning, machine
1950 learning (computer vision, robo cs (if total Turing test)
=> Psychological AI + Thinking Ra onally: by the study of ra onal processes of op miza on, such as logic systems
+ “law of thought”: 1) difficult to turn informal knowledge into formal terms; 2) difference in solving
problem in principle and in prac cal
+ Ac ng Ra onally: machine behave op mally, such as vacuum cleaner
+ “ra onal-agent”, the emphasis on correct inferences (more general than think ra onally, more
amenable to scien fic development
, History of Computer
metaphors for throughout history, it is believed mechanical
brain ac vity ancient Greece, "hydraulic metaphor" was used to compare the brain to a water pump or fountain.
during the Renaissance, mechanical like clockwork device, later steam engine
last century, as telephone exchange
now, computer (“The computer is the last metaphor; it need never be supplanted” - Johnson-Laird, 1983)
=> brain as hardware, physical device; mind as so ware, requires physical device to operate.
but is not material, has no mass
Wilhelm Schickard the 1st known calcula ng machine was constructed around 1623
(1592-1635)
Age of Enlightenment thought as reasoned calcula on, can even solve moral ques ons
(1700-1800)
Industrial Revolu on calcula on seemed as dull, repe ve
(1760-1840) talent, genius seemed as informal, roman c (Gaspard de Pony)
Go ried Wilhelm Leibniz Developed a calcula ng machine that could perform addi on, subtrac on, mul plica on, and division.
Gaspard de Prony + French Government set tables of accurate numbers
late 18th century + De Prony developing a mechanical calculator
workers, called “computers”, carry out calcula ons
+ Large-scale Manufacturing of Trigonometric Func ons (1790s)
Charles Babbage imagined calcula ons could be by a machine, rather than “workers”, 1st mechanical computer
1812 => “Mr. Babbage’s inven on puts an engine in place of the computer” (Colebrooke, 1825)
English mathema cian
The 1st opera onal programmable computer: Z-3 by Konrad Zuse, 1941 in Germany
The 1st electronic computer, the ABC by John Atanasoff and Clifford Berry (1940-1942)
ENIAC developed the most influen al forerunner of modern computer
The 1st programmer: Babbage’s colleague Ada Lovelace
Alan Turing + build the 1st opera onal computer: Heath Robinson
+ Turing consider the similarity “very superficial”
1912-1954 + 1943, same group developed Colossus in UK, general-purpose machine based on vacuum tubes
Cogni ve revolu on:
Mind/Brain as computer
<= The first work of AI
Warren McCulloch
Walter Pi s
1943
Marvin Minsky <= build the 1st neural network computer: SNARC
Dean Edmonds
1950
Donald Broadbent <= one of the 1st works to model psychological phenomena as informa on processing.
<Percep on and
Communica ons>
1958
Voordelen van het kopen van samenvattingen bij Stuvia op een rij:
Verzekerd van kwaliteit door reviews
Stuvia-klanten hebben meer dan 700.000 samenvattingen beoordeeld. Zo weet je zeker dat je de beste documenten koopt!
Snel en makkelijk kopen
Je betaalt supersnel en eenmalig met iDeal, creditcard of Stuvia-tegoed voor de samenvatting. Zonder lidmaatschap.
Focus op de essentie
Samenvattingen worden geschreven voor en door anderen. Daarom zijn de samenvattingen altijd betrouwbaar en actueel. Zo kom je snel tot de kern!
Veelgestelde vragen
Wat krijg ik als ik dit document koop?
Je krijgt een PDF, die direct beschikbaar is na je aankoop. Het gekochte document is altijd, overal en oneindig toegankelijk via je profiel.
Tevredenheidsgarantie: hoe werkt dat?
Onze tevredenheidsgarantie zorgt ervoor dat je altijd een studiedocument vindt dat goed bij je past. Je vult een formulier in en onze klantenservice regelt de rest.
Van wie koop ik deze samenvatting?
Stuvia is een marktplaats, je koop dit document dus niet van ons, maar van verkoper AliceOuterspace. Stuvia faciliteert de betaling aan de verkoper.
Zit ik meteen vast aan een abonnement?
Nee, je koopt alleen deze samenvatting voor €5,46. Je zit daarna nergens aan vast.
Is Stuvia te vertrouwen?
4,6 sterren op Google & Trustpilot (+1000 reviews)
Afgelopen 30 dagen zijn er 51292 samenvattingen verkocht
Opgericht in 2010, al 15 jaar dé plek om samenvattingen te kopen