Download Artificial Intelligence - Study Notes | CPSC 420 and more Study notes Computer Science in PDF only on Docsity!
CPSC 420-500 Artificial Intelligence
- Instructor: Yoonsuck Choe ([email protected])
- http://courses.cs.tamu.edu/choe/08fall/
- Office: HRBB 322B TR 2:00pm–3:00pm
- TA: Lei He
- Office: TBA
- All communications out of the class will be through email registered on NEO (neo.tamu.edu), and the announcements on the web page, so regularly check out the web page.
- Class notes will be available on the web 24 hours prior to the class. It is your responsibility to print it out and bring it to the class. http://courses.cs.tamu.edu/choe/08fall/420/lectures/ 1
Syllabus http://courses.cs.tamu.edu/choe/08fall/
- See handout (which is just a hardcopy of the web page on day 1).
2
Things You May Need
- Students with disability: Please contact the department office (HRBB 3rd floor) for assistance. See the syllabus for the full information.
- Computer (UNIX) accounts: If you don’t have one, get one: http://www.cs.tamu.edu/department/ policies/accounts Getting Your Money’s Worth
- Utilize your instructor and TA as much as possible.
- You have paid for their services.
What is Intelligence Textbook Definitions
- Thinking like humans
- Acting like humans
- Thinking rationally
- Acting rationally ← However, it depends on the definition: whatever the (intelligence) test tests.
What is AI?
A folk (popular) view of AI From http://www-2.cs.cmu.edu/afs/cs.cmu.edu/ user/zhuxj/www/travel/fun/ images/terminator.jpg (top); Universal studio’s movie “Terminator” (bottom)
5
But Really, What is AI? Diverse areas: http://www.aaai.org
- Problem solving
- Reasoning
- Theorem proving
- Learning
- Planning
- Knowledge representation
- Perception and Robotics
- Agents
- and more 6
Approaches
Two basic stances
- Strong AI:
- Build something that actually thinks intelligently.
- Simulation of thought would give rise to the pheonmenology of thought (i.e., how it feels like to think).
- Weak AI:
- Build something that behaves intelligently.
- Not worried about its feelings.
Problems
- Strong AI: Hard to determine if something is really consciously intelligent or not (the other minds problem in philosophy).
- Weak AI: Utility of the result is limited by the stated goal. Hard to achieve a general usefulness as in true intelligence.
Back to Reality
Let’s be realistic. :-)
- Study strategies employed by humans in dealing with real-world problems.
- These include all the topics listed earlier.
- The background you learn in this course will enable you to appreciate the deepness of the problems, and to pursue further interest in AI, and in human and machine intelligence in general.
13
Overview
• Related academic disciplines
• History of AI
• Hard Problems
• Current Trends
14
Foundations of AI
• Philosophy
• Mathematics
• Psychology
• Cognitive Science
• Linguistics
• Neuroscience
Philosophy of Mind The mind-body problem:
• Dualism: Mind and body are separate entities.
• Monism: Only mind or body exist, but not both
- Idealism: all things are mental
- Materialism: all things are material
• Epiphenomenalism: mental phenomena are just
side-effects of physical change in the brain (i.e. they do not have causal power over behavior). Too many variations to mention all.
Mathematics
• Algorithm (al-Khowarazmi)
• Boole
• Hilbert
• G ¨odel: Incompleteness theorem
• Turing: Halting problem
• Cook and Karp: P, NP, and the like
Representation/Interpretation, Symbol/Computing: the computer/software metahpore.
17
Psychology
• Behaviorism: stimulus-response and conditioning
• Functionalism: internal representations and
processes. Implementation independent.
• Perceptual psychology: vision, audition, etc.
• Cognitive psychology: cognition as information
processing.
• Holistic vs. localist debate: emergent vs. simple
summation.
18
Linguistics
• WW II : machine translation.
• Phonetics, syntactic theory, semantics, discourse,
etc.
• Innate vs. learned? : Chomsky
• Syntax: finite automata, context free grammar, etc.
• Semantics: semantic nets
• Sub-symbolic: self-organizing maps, episodic
memory, recurrent neural nets, etc.
Cognitive Science Interdisciplinary field studying human perception and cognition, ranging over:
- Neuroscience
- Behavioral science
- Social science
- Psychology
- Computational science
- Information theory
- Cultural studies
History of AI (III)
The 60’s and 70’s
• ELIZA
• Genetic algorithms
• Knowledge-based systems: avoid the weak method,
i.e. search
- scientific domain
- engineering domain
- natural language
The 80’s : 5th generation AI – Prolog.
25
History of AI (IV)
50th anniversary in 2006: http://en.wikipedia.org/wiki/AI@
• Some quotes from the 50th anniversary event (Rodney
Brooks):
- the social sophisitication of 10-year-old - the manual dexterity of a 6-year-old - the language ability of 4-year-old - the visual object recognition of a 2-year-old
26
Hard Problems (I)
• Physicalism, materialism, and naturalism: brain causes
mind.
• Functionlism: if it functions in the same way, a silicon brain
can also be conscious.
• Dualism and homunculus: the Cartesian theatre.
• Wide vs. narrow content: real correspondence, or limited
to experiential state?
• Intentionality: how can we believe in things that do not
exist, such as Poseidon.
Hard Problems (II)
• Semantic content and syntactic symbols: how can
syntacic constructs posess intenionality?
• Symbol grounding: sensory devices produce grounded
symbols, and composite symbols can be constructed.
• Problem of qualia: why do we feel in such a way?
• Turing test and Searle’s Chinese Room
Hard Problems (III)
• However, the assumption that a collection of unconscious
things are unconscious is invalid: think about organic vs. inorganic, life vsinanimate matter.
• Searle’s point of view: mind is an emergent phenomena of
the neural substrate (biological naturalism).
29
Current Trends
• Learning: instead of hand-coding or strict reasoning.
• Neural networks and statistical methods
• Genetic algorithms (Evolutionary algorithms)
• Embodied robotics; Dynamical systems approach
• Bioinformatics
• Computational Neuroscience
• Distributed Agents
• Some thoughts on consciousness: Crick and Koch
30
Unix Environment (Self Study)
The following slides are FYI: they won’t be covered in the class. If you have any question about these, please see the instructor or the TA.
- Remote access
- Shell
- Files and Directories
- File and Dir Permissions
- Customizing the environment
- Execution of programs
- Getting More Information
- Editor: pico
Remote Access
- Telnet (insecure) vs. SSH (secure)
- http://www.freessh.org/
- For windows, use PUTTY.EXE
- On-campus: sun.cs.tamu.edu, interactive.cs.tamu.edu , etc.
- Off-campus: Only by using TAMU VPN
- Use TAMU vpn to access other sunhosts.
File and Dir Perms
unix:˜/> ls -ltotal 568 -rw--------rwx------ 11 choechoe staffstaff 22016 Oct600 Nov (^) 20 17:371 11:26 AdobeFnt.lstPUTTY.RND* drwx-------rw------- 21 choechoe staffstaff 4096 Jan4869 Jan 14 22:249 09:34 RCS/aaai drwx------ 2 choe staff 4096 Jan 13 15:45 acct/
- snip^ * |{z}^ d dir or file
rwx | {z } owner |{z}^ rwx group
rwx | {z } other r: read, w: write, x: execute (allow cd for dir) permission.
37
Changing File and Dir Perms chmod [u|g|o][+|-][r|w|x] [file|dir]
- chmod o-rwx file
- You can also use octal: rwxr-xr-x == 111101101 (binary) == 755 (octal)
- chmod 600 filename rwx------
- chmod 755 dirname rwxr-xr-x Directory needs to be readable to do ls, and executable to do cd.
38
- Environment variables: Environment Variables - used to configure your env. - setenv gives you the list with their values - setenv VARNAME=value to define or reset - Append $ to get the value. - echo $VARNAME to view value
- Shell variables: use set
- Home directory (echo $HOME): - This is where all the action begins. - Everything below here belongs to you (almost).
Going to home: cd or cd ˜ or cd $HOME or ...
Customizing Your Shell In tcsh:
- .login : only executed when you first login.
- .cshrc : run everytime you create a sub-shell, i.e. running a shell within a shell.
- Basically a list of shell commands, like the BAT file. Just add these lines in /.login : setenv PATH "$HOME/bin:$PATH" set prompt="%m:%˜/> " alias ls "ls -F"
Execution of Programs
- ls is actually /usr/bin/ls.
- Because $PATH contains /usr/bin/, the above file gets executed.
- For local executables (compiled ones, etc.) in the current dir, add ./ to specify the current dir: ./execfilename
- This is not a concern because we’ll be using GCL interpreter: /usr/local/bin/gcl
41
Getting More Info
- Use the man command: man ls man chmod man mkdir
- Navigating in man pages: - space (or CTRL-F): pgdown - CTRL-B: pgup - /ENTER: search fwd for - ?ENTER: search bwd for - / or? alone: repeat search fwd or bwd 42
Editor: PICO
/opt/csw/bin/pico
An easy to use text editor: navigate with arrow keys, and CTRL-Y(pgup) and CTRL-V(pgdn). CTRL-X: Exit : answer carefully!. CTRL-O: Save As CTRL-R: Read another file into current position CTRL-K: Cut (you can cut multiple lines) CTRL-U: Paste (one or more lines cut with CTRL-K) CTRL-W: Search ( W here is ...) No undo(!): I recommend vi or emacs. Of course you may ftp. :-)
Tcsh tips
- Command and filename completion: just type a partial string and press [tab].
- Use arrow keys to go backward (like in doskey).
