Envisioning a Robust, Scalable Metacognitive Architecture Built on Dimensionality Reduction Scruffy Metacognition Jason B. Alonso 1 Kenneth C. Arnold 2,3 Catherine Havasi 3,2 1 Personal Robots Group MIT Media Laboratory 2 MIT Mind Machine Project 3 Software Agents Group MIT Media Laboratory AAAI-10 Workshop on Metacognition for Robust Social Systems July 2010 Alonso, Arnold, Havasi (MIT) Scruffy Metacognition Metacognition 2010 1 / 21
21
Embed
Envisioning a Robust, Scalable Metacognitive Architecture ...web.media.mit.edu/~kcarnold/scruffy-metacog/alonso-2010-AAAI10-MetacogSlides.pdfEnvisioning a Robust, Scalable Metacognitive
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Envisioning a Robust, Scalable MetacognitiveArchitecture Built on Dimensionality Reduction
Scruffy Metacognition
Jason B. Alonso1 Kenneth C. Arnold2,3 Catherine Havasi3,2
1Personal Robots GroupMIT Media Laboratory
2MIT Mind Machine Project
3Software Agents GroupMIT Media Laboratory
AAAI-10 Workshop on Metacognition for Robust Social SystemsJuly 2010
What function should each component perform?Connectionist answer (switches, or “neurons”) theoreticallysatisfying to some, practically less than enlighteningOur answer: pattern discovery and matching
One basic process of an intelligent system is to identify usefulpatterns in its input and its outputOne symbol ⇐⇒ one pattern
Summarizing many inputs and outputs with fewer symbols... in essence, dimensionality reduction
Planning can be a pattern completion problem that leveragesdimensionality reductionMetacognitive functions, particularly metaplanning, can be built onthese principles
Build a model of salient patterns inobservable events and behaviorsGenerate plans that achieve goalsgiven this modelIncremental. Learn/refine modelsfrom experience in real timeScruffy. Statistical handling ofsymbolic representations of the realworld to draw robust conclusionsIn practice, two approaches:
Replay of natural responses toenvironment and teammatesGoal-seeking
Detect instances ofpreviously-seen patternsRefine models for thosepatterns (or record newpattern)Describe timeline as acombination of understoodpatternsComplete timeline byinterpolating gaps in timeline
The difference between cognition and metacognition is in thewiring, permitting scalable architectures.Systems that build their own representations dynamically aremore robust.
When the astronaut player is engaged in a search activity with abunch of boxes, the robot is not about to hit the elevator callbutton.Correlation not causal, but reflective of teaming behaviorAnti-correlation not found in CBP or plan networks