Foundations of Artificial Intelligence 1. Introduction Organizational Aspects, AI in Freiburg, Motivation, History, Approaches, and Examples

Foundations of Artificial Intelligence
1. Introduction
Organizational Aspects, AI in Freiburg,
Motivation, History, Approaches, and Examples
Joschka Boedecker and Wolfram Burgard and
Frank Hutter and Bernhard Nebel
Albert-Ludwigs-Universität Freiburg
Apr 18, 2018

Organizational
Lectures:
Time:
Wed 10:15 – 12:00
Fri 10:15 – 12:00 (alternating
with the home work sessions)
Lecturers:
Prof. Dr. Joschka Boedecker
(jboedeck@informatik.uni-freiburg.de)
Prof. Dr. Wolfram Burgard
(burgard@informatik.uni-freiburg.de)
Prof. Dr. Frank Hutter
(fh@informatik.uni-freiburg.de)
Prof. Dr. Berhard Nebel
(nebel@informatik.uni-freiburg.de)
Home Work & Tutorials:
Time:
Fri 10:15 – 12:00 (English and
German groups)
→ See our Web page for
details, assignment!
Exercise sheets posted on Web
page. First session on April 27.
Organizers:
Tim Schulte, Michael Krawez
Credit Requirements:
Written exam (see Web page)
(University of Freiburg) Foundations of AI Apr 18, 2018 2 / 34

Lecture Material
Lectures are based on
Artificial Intelligence:
A Modern Approach, Third Edition
Stuart Russell and Peter Norvig
Copies of the slides, online recordings and further information can be found on the Web
page at
http://ais.informatik.uni-freiburg.de/teaching/ss18/ki/
Many illustrations are taken from the above-mentioned book. Some slides are based on
presentations created by Prof. Gerhard Lakemeyer, Univ. Aachen. Several sections were
originally prepared by Dr. Jana Köhler.

Course Contents
Strongly method-oriented
1. Introduction
2. Rational Agents
3. Solving Problems by Searching
4. Informed Search
5. Constraint Satisfaction Problems
6. Games
7. Propositional Logic
8. Satisfiability and Model Construction
9. Predicate Logic
11. Planning
12. Simple Probabilistic Reasoning
13. Machine Learning
14. Acting under Uncertainty

AI in Freiburg
Bernhard Nebel
Autonomous Intelligent Systems
Wolfram Burgard
Machine Learning
Frank Hutter
Neurorobotics
Joschka Boedecker

Junior Research Groups
Cognitive Modeling
Marco Ragni
Brain-Computer Interfaces
Michael Tangermann

Senior Staff Members (Among Further PostDocs)
Robert Mattmller
(AI Planning)
Christian Dornhege
(Robotics)
Marius Lindauer
(Algorithm Design)

Action planning: theory and practice
Fast planning systems (international competitions)
Applications for elevator systems and space
Theoretical results
Projects: CRC AVACS, Karis Pro (intra-logistics),
Kontiplan, Hybris
Qualitative temporal-spatial reasoning
Theory and reasoning algorithms
Application in qualitative layout description
(CRC “Spatial Cognition”)
RoboCup
World champion three times
Autonomous table soccer
RoboCup rescue (multi-agent-systems for disaster relief)
Cognitive robotics (BrainLinks-BrainTools)
Reasoning for human-centered robotics

Neurorobotics
Data-efficient Reinforcement
Learning
Representation Learning:
Deep Neural Networks (in
space and time)
Learning control of complex
dynamical systems like robots
or real neuronal networks
(BrainLinks-BrainTools)
Interpretation of brain signals
Industrial applications

Autonomous Intelligent Systems
Mobile robots
Probabilistic approaches for state
estimation and control
Adaptive techniques and learning
Multi-robot systems
Applications of mobile robots
Cognitive Robotics
Service robots

Brain State Decoding Lab
Brain-computer interfaces
Decoding of brain signals
Supervised learning
Adaptive unsupervised
classification
Learning in non-stationary
environments
Supervised subspace
decompositions
Mental workload assessment
e.g. of drivers
Predicting user performance
BCI-supported rehabilitation

Automated Algorithm Design
Machine Learning (ML)
AutoML: automatically selecting features,
ML algorithm & hyperparameters, ensembles
Currently AutoML world champions
Bayesian optimization
Meta-Learning: reasoning across datasets
Deep Learning: automatic feature engineering
Big Data: how to train efficiently?
Programming by Optimization
Algorithm Configuration
Algorithm Portfolios
Algorithm Runtime Prediction
Automatic science: what makes instances hard?
Applications: world champions
in SAT solving and AI planning competitions

Cognitive Modeling Lab
Cognitive models of human thinking,
reasoning, and planning
Qualitative Reasoning and imprecise
knowledge
Cognitive complexity analysis
Behavioural and fMRI experiments
Systems that solve IQ-test problems
“Build systems that reason and plan
like humans” 1 2 3 4
5 6 7 8
b

Studying AI in Freiburg
Machine Learning and Data Mining
Knowledge Representation
Introduction to Mobile Robotics
AI Planning
Logic
Game Theory
Neurorobotics
. . .

What is Artificial Intelligence?
The attempt to make computers more “intelligent”
The attempt to better understand human intelligence
Four approaches:
- Is it about thought thinking . . .
- . . . or acting?
- Oriented towards a human model (with all its defects) . . .
- . . . or normative (how should a rational being think/act)?

A Few Definitions
Thinking Humanly Thinking Rationally
“The exciting new effort to make computers
think . . . machines with minds, in the full
and literal sense.” (Haugeland, 1985)
“[The automation of] activities that we as-
sociate with human thinking, activities such
as decision-making, problem solving, learn-
ing . . . ” (Bellman, 1978)
“The study of mental faculties through the
use of computational models.” (Charniak
and McDermott, 1985)
“The study of the computations that make
it possible to perceive, reason, and act.”
(Winston, 1992)
Acting Humanly Acting Rationally
“The art of creating machines that perform
functions that require intelligence when per-
formed by people.” (Kurzweil, 1990)
“The study of how to make computers do
things at which, at the moment, people are
better.” (Rich and Knight, 1991)
“Computational Intelligence is the study of
the design of intelligent agents.” (Poole et
al., 1998)
“AI . . . is concerned with intelligent behavior
in artifacts.” (Nilsson, 1998)

The Turing Test
000
000
000
000
000
000
000
000
000
000
000
000
000
000
000
111
111
111
111
111
111
111
111
111
111
111
111
111
111
111 HAL 9000
?

Systems that Act Humanly
Reproducing human behavior
→ Prototype: Turing Test
→ . . . in AI, scarcely pursued
→ . . . but yearly competitions exist, e.g.,
Loebner Prize:
http://www.loebner.net/Prizef/loebner-prize.html

Loebner Prize Winner Three Times
Richard Wallace (http://www.alicebot.org)
Web page of Alice in 2000

Example Session with Alice (1)
What is your name?
> Wolfram
Nice to meet you Wolfram.
> Do you know Clinton?
He was the second Impeached President of the United States.
> Do you like him?
Sure he has never done anything to me.
> What is an impeachment?
It is a good question. I have to process that one for a while.
I would do a search for it.
...
> Who are you?
I ask myself that question, "Who am I?"
> What are you doing?
I am chatting with people on the net.
> What is your favorite topic?
My favorite subject is artificial intelligence.
> What is artificial intelligence?
Artificial intelligence is the branch of engineering and science devoted
to constructing machines that think. I can ask someone about it.
> Can you do anything else than chatting?
Doing anything else than chatting is not among my strongest traits.
...

Example Session with Alice (2)
...
> How old am I?
Is this a trick question? You said you were how many years old?
My guess is that you are really a kid.
> What would you like to know about me?
Tell me about your educational background.
> I am a professor in computer science.
You are a professor in computer science? How do you like your work?
> It is fun teaching courses on artificial intelligence.
I think it is a lot of fun.
> What should I tell the students about you?
Be sure to think before you speak. State your point clearly and slowly and
gauge the listener’s response before going any further.

Example Session with God (1)
Human: Do you know Obama?
God: I don’t know if I know it. Where would I have heard about it?
Human: He is the current president of the United States.
God: I did not know is it.
Human: Do you know Clinton?
God: He was the second Impeached President of the United States.
Human: What is an impeachment?
God: Charge against a public official of improper conduct.
...
Human: Who are you?
God: I am the Allmighty, God himself.
Human: What are you doing?
God: I am just killing time.
Human: What is your favorite topic?
God: My favorite subject is artificial intelligence.
Human: What is artificial Intelligence?
God: Artificial intelligence is the branch of engineering and
science devoted to constructing machines that think. That’s not
something I get asked all the time.
Human: Can you do anything else than chatting?
God: Doing anything else than chatting is not among my strongest
traits.

Example Session with God (2)
Human: My name is Wolfram.
God: OK I will call you Wolfram.
Human: Who am I?
God: You are Wolfram, seeker.
Human: How old am I?
God: Is this a trick question? You said you were years old? My
guess is that you are really a kid.
Human: What would you like to know about me?
God: Tell me about your educational background.
Human: I am a professor in Computer Science
God: What is your field?
Human: Artificial Intelligence
God: Do you mind if I tell other people you are teaching Artificial
Intelligence.
Human: No.
God: OK then I will add it to my gossip files.
Human: What should I tell the students about you?
God: I believe it is always best to say positive things to build
people up rather than negative things to bring people down.

Systems that Think Humanly
What cognitive capabilities are necessary to produce intelligent
performance?
Not important: Being able to solve problems correctly
Important: Being able to solve problems like a human would
→ Cognitive science and cognitive psychology
→ Also important for human-machine interaction
. . . will not be discussed in this course

Systems that Think Rationally
What are the laws of thought?
How should we think?
→ The logical approach
→ Problems:
Presentation of problem descriptions using a formal notation
Computability
→ These are problems that appear regardless of the formalization method

Systems that Act Rationally
→ Rational agents (or rational actors)
A rational agent acts so as to achieve its given goals, under the
assumption that its impressions of the world and its convictions are
correct
Rational thinking is a prerequisite for rational acting, although it is not
a necessary condition
→ What to do, for example, when we must make a decision faced with
insufficient information?

The AI Scene
Fields of Application Methods
Systems that can
understand and generate
speech
Systems that can
understand images
Robotics
Assistant systems
Problem solving and searching
Knowledge representation and
processing
Action planning
Machine learning
Handling uncertain knowledge
Neural networks
With interdisciplinary relationships to Mathematics, Philosophy, Psychology,
(Computational) Linguistics, Biology, Engineering Sciences, . . .

The Origins of AI
Since the beginning, Philosophy, Mathematics, Psychology, Linguistics,
and Computer Science have all
asked similar questions
developed methods and produced results for AI
The origins of AI (1943–1956): With the development of the first
computing systems, people began to wonder, “Can computers copy the
human mind? (Turing Test)”

50 Years of AI (1)
1956: Dartmouth Workshop - McCarthy proposes the term, “Artificial
Intelligence” - and early enthusiasm:
It is not my aim to surprise or shock you - but the simplest way I can
summarize is to say that there are now in the world machines that think,
that learn and that create. Moreover, their ability to do these things
is going to increase rapidly until - in the visible future - the range
of problems they can handle will be coextensive with the range to which
the human mind has been applied. [Simon, 1957]
60’s: “Intelligent Behavior” is shown in many demonstration systems for
micro-worlds (Blocks world)
70’s: Problems:
Systems for micro-worlds prove not scalable → “real” applications
“Intelligent behavior” requires much knowledge → knowledge-based
systems

50 Years of AI (2)
80’s: Commercial success of experimental systems (e.g. R1), intense
research support (e.g. Fifth generation computer systems project in
Japan), return to neural networks
End of the 80’s: Expert systems prove less promising than imagined,
(demystification of expert systems), end of the Fifth generation computer
systems project, “AI winter”
90’s: Inclusion of probabilistic methods, agent-oriented vision techniques,
formalization of AI techniques and increased use of mathematics in the
field
...gentle revolutions have occurred in robotics, computer vision,
machine learning (including neural networks), and knowledge
representation. A better understanding of the problems and their
complexity properties, combined with increased mathematical
sophistication, has led to workable research agendas and robust methods.
[Russell & Norvig, 1995]

. . . and Today?
Many coexisting paradigms
→ Reactive vs. deliberative approaches
→ Probabilistic vs. analytic
→ . . . often hybrid approaches as well
Many methods (partly from other disciplines):
→ Logic, decision theory, algorithms
Many approaches:
→ Theoretical, algorithmic experimentation, system-oriented
Today, many methods are no longer regarded as pure AI methods.
Examples: Board game programs, logic programming (PROLOG),
search procedures, . . .
Deep learning has become the new hype . . .

Examples: Algorithmic, Experimental Tasks
Many AI problems are inherently difficult (NP-hard), but it is possible, in
spite of this and with the use of good search techniques and heuristics, to
solve problem instances up to a certain size:
Satisfiability of boolean formulas
→ Randomized, local search techniques (up to 2,500???? variables in
complex instances)
Constraint propagation and backtracking techniques
→ Empirical and analytical comparisons of various techniques
Action planning
→ Empirical comparisons of various approaches and systems
. . .

Systems
Alongside theory and the analysis of individual algorithms, the building of
systems and applications is a basic point:
Herb Simon in a lecture entitled “How to become a good scientist”
(1998):
“Build a System”
Application of AI techniques to solve real problems
Study of the interaction of artefacts with their environment
Synergetic effects in systems

Systems
Computer Games
Navigation Systems
Smart phone services
Intelligent email
Search engines
Recommender systems
Self-driving cars
. . .

Foundations of Artificial Intelligence 1. Introduction Organizational Aspects, AI in Freiburg, Motivation, History, Approaches, and Examples

More Related Content

Similar to Foundations of Artificial Intelligence 1. Introduction Organizational Aspects, AI in Freiburg, Motivation, History, Approaches, and Examples (20)

More from cniclsh1 (20)

Recently uploaded (20)

Foundations of Artificial Intelligence 1. Introduction Organizational Aspects, AI in Freiburg, Motivation, History, Approaches, and Examples