Computational Models of Human Intelligence - PowerPoint PPT Presentation


PPT – Computational Models of Human Intelligence PowerPoint presentation | free to download - id: 9594b-NzNlN


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation

Computational Models of Human Intelligence


Can directly sense many kinds of human activities. Practical applications ... Location-Based Activity Recognition using Relational Markov Networks Lin Liao, ... – PowerPoint PPT presentation

Number of Views:53
Avg rating:3.0/5.0
Slides: 24
Provided by: cse190


Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Computational Models of Human Intelligence

Computational Models of Human Intelligence
  • Henry Kautz
  • Department of Computer Science
  • University of Rochester
  • Autumn 2007

A Dream of AI
  • Systems that can understand ordinary human
  • Work in KR, NLP, vision, IUI, planning
  • 1965 1985
  • Scripts and plan recognition
  • Knowledge-based computer vision
  • Critical problem scaling beyond microworlds
  • 1985 2000
  • Retreat to research on fundamentals of
    inference, learning, and perception

  • Resurgence of work in behavior recognition,
    fueled by
  • Advances in probabilistic inference
  • Graphical models
  • Scalable inference algorithms
  • KR unites with Bayes
  • Ubiquitous sensing devices
  • RFID, GPS, motes,
  • Can directly sense many kinds of human activities
  • Practical applications
  • Healthcare aging in place
  • Security
  • Consumer electronics

Growing Ubiquitous Sensing Infrastructure
  • GPS
  • Wi-Fi localization
  • RFID tags
  • Wearable sensors

Advances in Artificial Intelligence
  • Graphical models
  • Particle filtering
  • Belief propagation
  • Statistical relational learning

Crisis in Caring for the Cognitively Disabled
  • Epidemic of Alzheimers
  • Community integration of 7.5 million citizens
    with MR
  • 100,000 _at_ year disabled by TBI
  • Post-traumatic stress syndrome
  • Caregiver burnout

Levels of understanding
  • Physical movement
  • Hand touches cup
  • Behaviors
  • Drinking from a cup
  • Plans
  • Obtain cup Fill cup Drink from cup
  • Goals
  • Quench thirst

Dimensions of the behavior recognition problem
  • Keyhole versus interactive
  • Keyhole
  • Determine how an agents actions contribute to
    achieving possible or stipulated goals
  • No model of the observer fly on the wall
  • Interactive
  • Actions performed by an agent to signal to
    another agent
  • Speech acts
  • Model social conventions agents models of
    other agents

Dimensions of the plan recognition problem
  • Ideal versus fallible agents
  • Mistaken beliefs
  • John drives to Reagan, but flight leaves Dulles.
  • Cognitive errors
  • Distracted by the radio, John drives past the
  • Irrationality
  • John furiously blows his horn at the car in front
    of him.

Dimensions of the plan recognition problem
  • Reliable versus unreliable observations
  • Theres a 80 chance John drove to Dulles.
  • Open versus closed worlds
  • Fixed plan library?
  • Fixed set of goals?
  • Metric versus non-metric time
  • John enters a restaurant and leaves 1 hour later.
  • John enters a restaurant and leaves 5 minutes
  • Single versus multiple ongoing plans

Dimensions of the plan recognition problem
  • Desired output
  • Set of consistent plans or goals?
  • Most likely plan or goal?
  • Most critical plan or goal?
  • Interventions observer should perform to aid or
    hinder the agent?

(Some) formalisms used to model human behavior
  • Consistency-based
  • Scripts hypothesize revise
  • Plan libraries Closed-world reasoning
  • Probabilistic
  • Bayesian networks
  • Hidden Markov models
  • Dynamic Bayesian networks
  • Stochastic grammars
  • Conditional random fields
  • Statistical-relational models

Scripts hypothesize revise
  • The Plan Recognition Problem C. Schmidt, 1978

Plan libraries closed-world reasoning
  • A Formal Theory of Plan Recognition and its
    Implementation Henry Kautz, 1991

Bayesian Networks
  • E. Horvitz, J. Breese, D. Heckerman, D. Hovel,
    and K. Rommelse. The Lumiere Project Bayesian
    User Modeling for Inferring the Goals and Needs
    of Software Users. Proceedings of the Fourteenth
    Conference on Uncertainty in Artificial
    Intelligence, July 1998.

Hidden Markov Models
D. Patterson, H. Kautz, D. Fox, ISWC 2005
Layered hidden Markov models
  • N. Oliver, E. Horvitz, and A. Garg. Layered
    Representations for Recognizing Office Activity,
    Proceedings of the Fourth IEEE International
    Conference on Multimodal Interaction (ICMI 2002)

Stochastic grammars
  • Darnell Moore and Irfan Essa, "Recognizing
    Multitasked Activities from Video using
    Stochastic Context-Free Grammar", AAAI-02, 2002.

Dynamic Bayesian Nets
Cognitive mode normal, error
Learning and Inferring Transportation Routines
Lin Liao, Dieter Fox, and Henry Kautz, Nineteenth
National Conference on Artificial Intelligence,
San Jose, CA, 2004.
Relational Conditional Random Fields
Location-Based Activity Recognition using
Relational Markov Networks  Lin Liao, Dieter Fox
and Henry Kautz.  Proceedings of the Nineteenth
International Joint Conference on Artificial
Intelligence, Edinburgh, Scotland, 2005.
Assisted cognition
Computer systems that improve the independence
and safety of people suffering from cognitive
limitations by
  • Understanding human behavior from low-level
    sensory data
  • Using commonsense knowledge
  • Learning individual user models
  • Actively offering prompts and other forms of help
    as needed
  • Alerting human caregivers when necessary
  • http//www.cs.rocheste

General architecture for model-based assistive
common-sense knowledge
decision making
user profile
physical behavior
Laboratory for Assisted Cognition Environments
  • Henry Kautz
  • Sangho Park, research scientist
  • Craig Harmon, lab manager
  • Joseph Modayil, post doc
  • Research
  • Robust behavior recognition using multiple
    sensors (vision, RFID, motion, )
  • Applications smart environments for support of
    persons with Alzheimers Disease, autism, and
    traumatic brain injury