COMP 424 – Artificial Intelligence What is Artificial Intelligence?
Instructors: Jackie CK Cheung
Copyright By PowCoder代写 加微信 powcoder
Outline for Today
• Biological and artificial intelligence
• Overview of AI history
• Examples of AI applications
What is Intelligence?
Possible Aspects of Intelligence
• Acquire, retain, and apply knowledge
• Apply logic and reason
• Be able to change and manipulate one’s environment
• Be able to adapt, foresee, and plan
• Be able to deal with uncertainty
• Possible modalities of intelligence:
• Spatial, verbal, logical, musical, social, …
One Model: Biological Intelligence
• Sensory processing:
• Visual cortex.
• Auditory cortex.
• Somatosensory cortex.
• Motor cortex.
• Cognitive functions:
• Reasoning.
• Executive control.
• Learning.
• Language.
Biological Intelligence
• A mix of general-purpose and special-purpose algorithms.
• General-purpose:
• Memory formation, updating, retrieval.
• Learning new tasks.
• Special-purpose:
• Recognizing visual patterns.
• Recognizing sounds.
• Learning language.
• All are integrated seamlessly!
What is AI?
What is AI?
• Sensory processing:
• Visual cortex
• Auditory cortex
• Somatosensory cortex
• Motor cortex
• Cognitive functions
• Reasoning
• Executive control
• Learning
• Language
Human intelligence:
Human intelligence:
• Sensory processing:
• Visual cortex
• Auditory cortex
• Somatosensory cortex
• Motor cortex
• Cognitive functions
• Reasoning
• Executive control
• Learning
• Language
Artificial Intelligence:
→ Computer vision
→ Signal/speech processing → Haptics
→ Robotics
→ Knowledge representation → Search, inference
→ Planning, decision-making → Model learning
→ Language understanding
What is AI?
Human intelligence:
• Sensory processing:
• Visual cortex
• Auditory cortex
• Somatosensory cortex
• Motor cortex
• Cognitive functions
• Reasoning
• Executive control
• Learning
• Language
Artificial Intelligence:
→ Computer vision
→ Signal/speech processing → Haptics
→ Robotics
→ Knowledge representation → Search, inference
→ Planning, decision-making → Model learning
→ Language understanding
What is AI?
Possible Goals of AI
• Modeling or replicating human cognition using computers.
• Replicating human behaviours using computers
• Studying problems that others don’t know how to solve.
• Cool stuff!
• Game playing, machine learning, data mining, speech recognition, computer vision, web agents, robots
• Useful stuff!
• Medical diagnosis, fraud detection, genome analysis, object identification, space shuttle scheduling, information retrieval
Goals of AI
Thinking Humanly
Thinking Rationally
Acting Humanly
Acting Rationally
Different Goals of AI
What is one major obstacle to investigating these goals?
Thinking Humanly
Thinking Rationally
Acting Humanly
Acting Rationally
This would be pretty awesome!
Different Goals of AI
Thinking Humanly
Thinking Rationally
Acting Humanly
Acting Rationally
Acting Humanly
• AI is about duplicating what the (human) brain DOES.
• (1912-1954) had interesting thoughts about this.
Can a machine think? -> If it could, how would we tell?
Turing (1950): “Computing machinery and intelligence”
Human interrogator
An operator interacts with either the human or the AI agent. Can he correctly guess which one?
Turing’s Prediction
• By 2000, a machine would have a 30% chance of fooling a lay person for 5 minutes.
• This actually happened in 2014: http://www.bbc.com/news/technology-27762088
• Does this mean that we have solved AI?
• Suggested major components of AI:
• Knowledge representation, automated reasoning, language understanding, machine learning
AI = Acting Humanly?
• Humans have biological resource constraints • Limited memory, thinking speed, attention span…
• Humans are often irrational
• Or else we do not understand our own notion of rationality
• e.g., don’t act towards our own goals; hold contradictory beliefs or preferences
• Kahneman and Tversky demonstrate ways that people are systematically irrational.
Optical Illusions
• Do we really want AI systems to replicate all of the features of human perception and cognition?
• E.g., visual system: https://michaelbach.de/ot/mot-breathingSquare/index.html
https://en.wikipedia.org/wiki/Ponzo_illusion
Different Goals of AI
Thinking Humanly
Thinking Rationally
Acting Humanly
Acting Rationally
Let’s try this!
Acting Rationally
• Rational behaviour = doing the “right” thing.
• Doing what is expected to maximize goal achievement,
given the available information and available resources.
This is the flavour of AI we will focus on.
Finally, Our Working Definition of AI
• Developing models and algorithms that can produce rational behaviours in response to incoming stimuli and information.
Rational Agents
This course is about designing rational agents.
• An agent is an entity that perceives and acts.
• Goal: Learn a function mapping percept histories to actions:
f : Ph → A
A rational agent implements this function such as to maximize performance.
• Performance measures: goal achievement, resource consumption, … Caveat: Resource constraints (time, space, energy,
bandwidth, …) which make perfect rationality unachievable
Objective: Find best function for given information and resources
Course Topics of COMP 424
• Search Basic tools
• Game playing
• Logical reasoning
• Classical planning
• Probabilistic reasoning
• Learning probabilistic models
• Causal probabilistic models
• Reasoning with utilities
• Sequential reasoning and decision-making.
• Applications
Logical representations
Probabilistic representations
Utility theory
AI Beginnings
• ENIAC: First super-computer, created in 1946.
• Early work in 1950s:
• Rosenblatt’s perceptron
• Samuel’s checkers player
Dartmouth Conference (1956)
Dartmouth Conference (1956)
• Some of the attendees:
• Carthy: LISP, time-sharing, application of logic
to reasoning
• : popularized neural networks and showed their limits, introduced slots and frames
• : information theory, juggling machine
• and Herb Simon: bounded rationality,
general problem solver, SOAR
• The meeting coined the term “artificial intelligence”
Early AI Hopes and Dreams
• Make programs that exhibit similar signs of intelligence as people: prove theorems, play chess, have a conversation.
• Logical reasoning was key.
• Learning from experience was considered important.
• The research agenda was geared towards building general problem solvers.
• There was a lot of hope that natural language could be easily understood and processed.
AI Downswings
• Early successes did not scale up!
1966 1973, 1974 1987-1993
Demos were impressive, but only worked in a narrow domain e.g., Machine translation for general texts
Perceived failure of machine translation
Major cut in AI research funding
“AI Winter”: many companies working in AI fail
• Much progress actually made in this period, but overpromising of results led to disappointments
Recent AI: Statistics to the Rescue!
• Heavy use of probability theory, decision theory, statistics.
• Trying to solve specific problems rather than aim for general
reasoning.
• AI today is a collection of sub-fields:
• Perception and computer vision.
• Natural language understanding. • Robotics
• Reasoning is now the part named “AI”.
• A lot of progress was made in this way!
• Some recent efforts try to put all this together
AI system (1997): Chess playing
IBM Deep Blue defeats .
• Perception: advanced features of the board.
• Actions: choose a move.
• Reasoning: search and evaluation of
possible board positions.
www.bobby-fischer.net
http://www-03.ibm.com
AI system (2008): Poker playing
University of Alberta’s Polaris defeats some of the world’s best online pros.
• One variety of poker: Heads-up limit Texas Hold’em (two players, limited betting amounts)
• Perception: features of the game.
• Actions: choose a move.
• Reasoning: search and evaluation of possible moves, machine
http://poker.cs.ualberta.ca/
AI system (2011): Jeopardy!
AI system (2015): Atari
Similar video on YouTube: https://www.youtube.com/watch?v=V1eYniJ0Rnk&ab_channel=TwoMinutePapers
AI system (2017): Self-Play for Go
AI system (2021): AlphaFold
Predict protein structure from amino acid sequences (Partial) solution to a 50 year old problem
Source: Nature
So, is AI solved?
Online Demo Released
• https://app.inferkit.com/demo
AI system (2014): City driving
Google cars have logged over 700,000 miles in autonomous mode
• Sensors and actuators similar to Stanley (GPS, 3D laser point cloud, cameras, odometry)
• Significant prior knowledge: City of Mountain View (12-square-mile) is fully mapped at high resolution.
How Do We Trust AI?
• Need to temper the hype!
• What kinds of problems do current AI technology solve?
• What are their limitations?
• How can we trust AI, when they can fail dramatically and unexpectedly?
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com