Artificial Intelligence Course: Overview, Topics, and Study Tips, Slides of Artificial Intelligence

Download Artificial Intelligence Course: Overview, Topics, and Study Tips and more Slides Artificial Intelligence in PDF only on Docsity!

Lecture 0 of 41

A Brief Survey of Artificial Intelligence

Course Outline

• Overview: Intelligent Systems and Applications
• Artificial Intelligence (AI) Software Development Topics
  • Knowledge representation
    • Logical
    • Probabilistic
  • Search
    • Problem solving by (heuristic) state space search
    • Game tree search
  • Planning: classical, universal
  • Machine learning
    • Models (decision trees, version spaces, ANNs, genetic programming)
    • Applications: pattern recognition, planning, data mining and decision support
  • Topics in applied AI
    • Computer vision fundamentals
    • Natural language processing (NLP) and language learning survey
• Practicum (Short Software Implementation Project)

• Problem Area
  • What are intelligent systems and agents?
  • Why are we interested in developing them?
• Methodologies
  • What kind of software is involved? What kind of math?
  • How do we develop it (software, repertoire of techniques)?
  • Who uses AI? (Who are practitioners in academia, industry, government?)
• Artificial Intelligence as A Science
  • What is AI?
  • What does it have to do with intelligence? Learning? Problem solving?
  • What are some interesting problems to which intelligent systems can be applied?
  • Should I be interested in AI (and if so, why)?
• Today: Brief Tour of AI History
  • Study of intelligence (classical age to present), AI systems (1940-present)
  • Viewpoints: philosophy, math, psychology, engineering, linguistics

Questions Addressed

What is AI? [1]

• Four Categories of Systemic Definitions
  • 1. Think like humans
  • 2. Act like humans
  • 3. Think rationally
  • 4. Act rationally
• Thinking Like Humans
  • Machines with minds (Haugeland, 1985)
  • Automation of “decision making, problem solving, learning…” (Bellman, 1978)
• Acting Like Humans
  • Functions that require intelligence when performed by people (Kurzweil, 1990)
  • Making computers do things people currently do better (Rich and Knight, 1991)
• Thinking Rationally
  • Computational models of mental faculties (Charniak and McDermott, 1985)
  • Computations that make it possible to perceive , reason , and act (Winston, 1992)
• Acting Rationally
  • Explaining, emulating intelligent behavior via computation (Schalkoff, 1990)
  • Branch of CS concerned with automation of intelligent behavior (Luger and Stubblefield, 1993)

What is AI? [3]

Viewpoints on Defining Intelligence

• Genuine versus Illusory Intelligence
  • Can we tell?
    • If so, how?
    • If not, what limitations do we postulate?
  • The argument from disability (“a machine can never do X”)
• Turing Test Specification
  • Objective: develop intelligent system “indistiguishable from human”
    • Blind interrogation scenario (no direct physical interaction – “teletype”)
    • 1 AI system, 1 human subject, 1 interrogator
    • Variant: total Turing Test (perceptual interaction: video, tactile interface)
  • Is this a reasonable test of intelligence?
  • Details: Section 26.3, R&N
  • See also: Loebner Prize page
• Searle’s Chinese Room
  • Philosophical issue: is (human) intelligence a pure artifact of symbolic manipulation?
  • Details: Section 26.4, R&N
  • See also: consciousness in AI resources

What is AI? [3]

Thinking and Acting Rationally

• Concerns: Human Performance (Figure 1.1 R&N, Right-Hand Side)
  • Top: thought processes and reasoning (learning and inference)
  • Bottom: behavior (interacting with environment)
• Computational Cognitive Modelling
  • Rational ideal
    • In this course: rational agents
    • Advanced topics: learning, utility theory, decision theory
  • Basic mathematical, computational models
    • Decisions: automata (Chomsky hierarchy – FSA, PDA, LBA, Turing machine)
    • Search
    • Concept learning
• Acting Rationally: The Rational Agent Approach
  • Rational action: acting to achieve one’s goals, given one’s beliefs
  • Agent: entity that perceives and acts
  • Focus of next lecture
    • “Laws of thought” approach to AI: correct inferences (reasoning)
    • Rationality not limited to correct inference

Why Study Artificial Intelligence?

• New Computational Capabilities
  • Advances in uncertain reasoning, knowledge representations
  • Learning to act: robot planning, control optimization, decision support
  • Database mining: converting (technical) records into knowledge
  • Self-customizing programs: learning news filters, adaptive monitors
  • Applications that are hard to program: automated driving, speech recognition
• Better Understanding of Human Cognition
  • Cognitive science: theories of knowledge acquisition (e.g., through practice)
  • Performance elements: reasoning (inference) and recommender systems
• Time is Right
  • Recent progress in algorithms and theory
  • Rapidly growing volume of online data from various sources
  • Available computational power
  • Growth and interest of AI-based industries (e.g., data mining/KDD, planning)

Relevant Disciplines

• Machine Learning
• Bayesian Methods
• Cognitive Science
• Computational Complexity Theory
• Control Theory
• Economics
• Neuroscience
• Philosophy
• Psychology
• Statistics

Artificial

Symbolic Representation Intelligence

Planning/Problem Solving Knowledge-Guided Learning

Bayes’s Theorem Missing Data Estimators

PAC Formalism Mistake Bounds

Inference NLP / Learning

Planning, Design Optimization Meta-Learning

Game Theory Utility Theory Decision Models

ANN Models Learning

Logical Foundations Consciousness

Power Law of Practice Heuristics

Bias/Variance Formalism Confidence Intervals Hypothesis Testing

Rule and Decision Tree Learning

• Example: Rule Acquisition from Historical Data
• Data
  • Customer 103 (visit = 1): Age 23, Previous-Purchase: no, Marital-Status: single, Children: none, Annual-Income: 20000, Purchase-Interests: unknown , Store- Credit-Card: no, Homeowner: unknown
  • Customer 103 (visit = 2): Age 23, Previous-Purchase: no, Marital-Status: married, Children: none, Annual-Income: 20000: Purchase-Interests: car, Store-Credit- Card: yes, Homeowner: no
  • Customer 103 (visit = n): Age 24, Previous-Purchase: yes, Marital-Status: married, Children: yes, Annual-Income: 75000, Purchase-Interests: television, Store-Credit-

Card: yes, Homeowner: no, Computer-Sales-Target: YES

• Learned Rule
  • IF customer has made a previous purchase , AND customer has an annual income over $25000 , AND customer is interested in buying home electronics THEN probability of computer sale is 0.
  • Training set: 26/41 = 0.634, test set: 12/20 = 0.
  • Typical application: target marketing

Text Mining:

Information Retrieval and Filtering

• 20 USENET Newsgroups
  • comp.graphics misc.forsale soc.religion.christian sci.space
  • comp.os.ms-windows.misc rec.autos talk.politics.guns sci.crypt
  • comp.sys.ibm.pc.hardware rec.motorcycles talk.politics.mideast sci.electronics
  • comp.sys.mac.hardware rec.sports.baseball talk.politics.misc sci.med
  • comp.windows.x rec.sports.hockey talk.religion.misc
  • alt.atheism
• Problem Definition [Joachims, 1996]
  • Given: 1000 training documents (posts) from each group
  • Return: classifier for new documents that identifies the group it belongs to
• Example: Recent Article from comp.graphics.algorithms Hi all I'm writing an adaptive marching cube algorithm, which must deal with cracks. I got the vertices of the cracks in a list (one list per crack). Does there exist an algorithm to triangulate a concave polygon? Or how can I bisect the polygon so, that I get a set of connected convex polygons. The cases of occuring polygons are these: ...
• Performance of Newsweeder (Naïve Bayes): 89% Accuracy

Related Online Resources

• Research
  • KSU Laboratory for Knowledge Discovery in Databases http://www.kddresearch.org (see especially Group Info, Web Resources)
  • KD Nuggets: http://www.kdnuggets.com
• Courses and Tutorials Online
  • At KSU
    • CIS732 Machine Learning and Pattern Recognition http://www.kddresearch.org/Courses/Fall-2002/CIS
    • CIS830 Advanced Topics in Artificial Intelligence http://www.kddresearch.org/Courses/Spring-2002/CIS
    • CIS690 Implementation of High-Performance Data Mining Systems http://ringil.cis.ksu.edu/Courses/Summer-2002/CIS
  • Other courses: see KD Nuggets, www.aaai.org, www.auai.org
• Discussion Forums
  • Newsgroups: comp.ai.*
  • Recommended mailing lists: Data Mining , Uncertainty in AI
  • KSU KDD Lab Electronic Groups: http://groups.yahoo.com/group/ksu-kdd

A Generic

Intelligent Agent Model

Agent Sensors

Effectors

Preferences Action

Internal Model (if any)^ Environment

Knowledge about World

Knowledge about Actions

Observations

Predictions

Expected Rewards

Term Project Topics

• Intelligent Agents
  • Game-playing: rogue-like (Nethack, Angband, etc.); reinforcement learning
  • Multi-Agent Systems and simulations; robotic soccer (e.g., Teambots)
• Probabilistic Reasoning and Expert Systems
  • Learning structure of graphical models (Bayesian networks)
  • Application of Bayesian network inference
    • Plan recognition, user modeling
    • Medical diagnosis
  • Decision networks or other utility models
• Probabilistic Reasoning and Expert Systems
• Constraint Satisfaction Problems (CSP)
• Soft Computing for Optimization
  • Evolutionary computation, genetic programming, evolvable hardware
  • Probabilistic and fuzzy approaches
• Game Theory

Homework 1:

Machine Problem

• Due: 10 Sep 2004
  • Submit using new script (procedure to be announced on class web board)
  • HW page: http://www.kddresearch.org/Courses/Fall-2004/CIS730/Homework
• Machine Problem: Uninformed (Blind) vs. Informed (Heuristic) Search
  • Problem specification (see HW page for MP document)
    • Description: load, search graph
    • Algorithms: depth-first, breadth-first, branch-and-bound, A search*
    • Extra credit: hill-climbing, beam search
  • Languages: options
    • Imperative programming language of your choice (C/C++, Java preferred)
    • Functional PL or style (Haskell, Scheme, LISP, Standard ML)
    • Logic program (Prolog)
  • MP guidelines
    • Work individually
    • Generate standard output files and test against partial standard solution
  • See also: state space, constraint satisfaction problems