Download Understanding the Capabilities & History of AI and more Lecture notes Algorithms and Programming in PDF only on Docsity!
08/03/
- Puan Zahriah Binti Sahri
- Office: Level G, KI wing
- Contact Details:
- Course Evaluation:
- 15% Project
- 20% Mid-term test
- 10% Quizzes (2)
- 10% Assignment
- 10% Tutorial
- 5% Lab test
- 30% Final exam
Artificial Intelligence (BITI1113)
Course Overview
08/03/
Artificial Intelligence (BITI1113)
Learning Outcomes
1 - Explain the definition of AI and its
techniques.
2 - Identify the types of AI Techniques.
3 - Use AI techniques in problem
solving.
Artificial Intelligence Chapter 1 : Introduction
What is
Intelligence
Humans are good at recognizing patterns
Aspects of Intelligence
Humans are good at understanding even difficult handwritings - thus human recognition capability is robust
Examples and Aspects Biological Intelligence
- Self-repair
- Self-guidance
- Reproduction
- Making decisions
- Reasoning capability
- Predicting/forecasting
- Understanding noisy or
fuzzy information
- Capability to Learn
- Capability to
Generalize/Classify
- Capability to Survive
- Gathering of Information
- Recognizing Patterns
- Common Sense
- Logical Thinking
Humans have self-repair (self response/ reactions) mechanisms in their bodies
Academic Disciplines relevant to AI
- Philosophy Logic, methods of reasoning, mind as physical system, foundations of learning, language, rationality.
- Mathematics Formal representation and proof, algorithms, computation, (un)decidability, (in)tractability
- Probability/Statistics modeling uncertainty, learning from data
- Economics utility, decision theory, rational economic agents
- Neuroscience neurons as information processing units.
- Psychology/ how do people behave, perceive, process cognitive Cognitive Science information, represent knowledge.
- Computer building fast computers engineering
- Control theory design systems that maximize an objective function over time
- Linguistics knowledge representation, grammars
History of AI
- 1943: early beginnings
- McCulloch & Pitts: Boolean circuit model of brain
- http://www.mind.ilstu.edu/curriculum/mcp_neurons/mcp_neuron_ 1.php
- 1950: Turing
- Turing's "Computing Machinery and Intelligenceā
- 1956: birth of AI
- Dartmouth meeting: "Artificial Intelligenceā name adopted
- 1950s: initial promise
- Early AI programs, including
- Samuel's checkers program http://www.fierz.ch/samuel.htm
- Newell & Simon's Logic Theorist
- 1955 - 65: āgreat enthusiasmā
- Newell and Simon: GPS, general problem solver
- Gelertner: Geometry Theorem Prover
- McCarthy: invention of LISP
Success Stories
- Deep Blue defeated the reigning world chess champion Garry
Kasparov in 1997
- During the 1991 Gulf War, US forces deployed an AI logistics
planning and scheduling program that involved up to 50,
vehicles, cargo, and people
- NASA's on-board autonomous planning program controlled the
scheduling of operations for a spacecraft
- Proverb solves crossword puzzles better than most humans
- Robot driving: DARPA grand challenge 2003-2007 (next slide)
- 2006: face recognition software available in consumer cameras
Example: DARPA Grand Challenge
- Grand Challenge
- Cash prizes ($1 to $2 million) offered to first robots to complete a long course completely unassisted
- Stimulates research in vision, robotics, planning, machine learning, reasoning, etc
- 2004 Grand Challenge:
- 240km (150 miles) route in Nevada desert
- None finished the route, Red team robot completed about 7 miles.
- ā¦ but hardest terrain was at the beginning of the course
- 2005 Grand Challenge:
- 132 mile race
- Narrow tunnels, sharp left and right turns, and winding mountain passes
- Stanford 1st, CMU 2nd, both finished in about 6 hours
- 2007 Urban Grand Challenge
- 96km (60 miles) urban area course in Victorville, California
- vehicles must obey all traffic laws while they detect and avoid other robots on the course
2004: Barstow, CA, to Primm, NV
150 mile off-road robot race across the Mojave desert Natural and manmade hazards No driver, no remote control No dynamic passing Fastest vehicle wins the race (and 2 million dollar prize)
Can we build hardware as complex as the brain?
- How complicated is our brain?
- a neuron, or nerve cell, is the basic information processing unit
- estimated to be on the order of 10 12 neurons in a human brain
- many more synapses (10 14 ) connecting these neurons
- cycle time: 10 -^3 seconds (1 millisecond)
- How complex can we make computers?
- 108 or more transistors per CPU
- supercomputer: hundreds of CPUs, 10^12 bits of RAM
- cycle times: order of 10 -^9 seconds
- Conclusion
- YES: in the near future we can have computers with as many basic processing elements as our brain, but with - far fewer interconnections (wires or synapses) than the brain - much faster updates than the brain
- but building hardware is very different from making a computer behaves like a brain!
