Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Applied Artificial Intelligence

Instructional Planning
by

Stephanie Frost

on 18 March 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Applied Artificial Intelligence

Stephanie Frost Applied Artificial Intelligence:
Instructional Planning Instructional Planning D. R. Peachey and G. I. McCalla. Using planning techniques in intelligent tutoring systems. International Journal of Man-Machine Studies, 24(1):77 – 98, 1986. Hello Hi, I'm Steph, M.Sc. student
14 years eLearning industry
Supervisor Dr. Gord McCalla
Passion is Instructional Planning Knowledge Representation Learning Object The Ecological Approach Input Bird Magpie "is a" Public domain image by Arpingstone "is a" Wing "has a" Task Domain Ontology teach breadth-first or depth-first?
more collaborative or indepentdent activities?
"free exploration" or system-directed? "has a" Crow Image under Creative Commons license
from Wikimedia Commons by Wsiegmund Earliest Research in this area (1984) Decision Theoretic Instructional Planner States system's belief about the tutoring situation
ex: studentKnows(X), studentReplies(Y) Actions N. Matsuda and K. VanLehn. Decision theoretic instructional planner for intelligent tutoring systems. Proc. for Workshop on Modeling Human Teaching Tactics and Strategies, ITS2000, pages 72–83, 2000. decisions the system makes
ex: teach a certain concept, agree with a student response Event unexpected actions taken by student
ex. student asks a question Influence Diagram Markov Decision Process procedure for making decisions (Actions) based on information available (States, Events) Utility small bonus if a student learns a concept
large bonus if student justifies their response
small punishment for each step required
very large punishment if student gives incorrect response
etc Reward Function knows(Wing)
knows(Crow)
... S D U Pedagogical Strategy Student Model G. McCalla. The ecological approach to the design of e-learning environments: Purpose- based capture and use of information about learners. Journal of Interactive Media in Education, 7:1–23, 2004. IEEE 1484.12.1 Learning Object Metadata (Published 2002)
Image from Wikimedia Commons by Rjgodoy Leveraging WWW Content Each time a student uses a learning object, a "stamp" of their student model is saved on it. Save anything that impacts personalization
current goal
beginner or advanced?
what friends told me about it Ecological Approach Metadata metadata My Thesis
Instructional Planner
using the EA EA metadata Output Simulation model Path through the LOs (sequence) Approach Recommender system Swarm Intelligence Constraint Satisfaction On Simulations Path Quality Example a path where the student learned lots of concepts in minimum time Think One thing that stood out for you
Anything you want to ask a grad student in AI?
Is this what you expected?
Anything you still want to know? Pair Similarities / Differences Share Bird Flocking Each bird follows three rules:
1. Don't get too close to other birds
2. Try to move toward the centre of neighbouring group of birds
3. Try to fly at the same speed as neighbouring birds A problem in many disciplines astronomy, geophysics, paleontology Can't conduct reproducible experiments Solution: Use Emergence 3 rules bird flocking behaviour ??? rules empirical observations guess at how human learning works Does whatever emerges from the model match real world data?
Full transcript