Houses of Mirrors: Deeply

blabbedharborIA et Robotique

23 févr. 2014 (il y a 3 années et 10 mois)

59 vue(s)

Houses of Mirrors: Deeply
Adaptive Designs for Machine
Cognition

Deborah Duong, Michael Ross

Next for MICCE: Ontological Level


Emergence of Data Driven Ontologies
from Text


Looking for High Independence of
grouping and low variance within
groupings


In other words, the highest mutual
information, lowest entropy grouping

Social Hierarchies


At INSCOM, subsumption hierarchical
trees of roles and role relations


Entities grouped into roles


Paths grouped into role relations


isa relations:


Black
-
market
-
merchant isa merchant

MICCE finds Systems


Finds systemic relations in common to similar
processes


Common paths between roles become role
relations


Higher levels of hierarchy have more abstract
processes.


Happen to be social systems at INSCOM


Regular Structural Equivalence in Social
Networks


Can help to find terrorist organizations

Ontologies


Users may browse data in terms they are
used to, at any level of generalization


Ex. The query: “terrorists bombing civilians”
can find “Joe suicide
-
vest
-
bombing subway
-
riders”


Hierarchy gives AI programs a gradient, a
measure of semantic distance from every
concept to every other concept, making
the space navigable.

Concepts of Concepts


We will implement ontologies by sending
concepts through the feedback loop


Concepts will form based on similarity,
split based on variance


Concepts become more independent as
dependent concepts are merged


With iteration concepts will become more
like orthogonal bases


Greater Independence


More accurate semantic distance
computed


Helps to minimize variance


Example: Taking cosine coefficient with
50 synonyms for a word rather than a
single concept that combines them


Calculations more accurate because we
don’t make false distinctions due to noise

Another Level of Feedback


Types of Feedback


Side
-
to
-
Side: Between entity and link assignments


Upper
-
Lower: Between parse, word sense, ontological levels


We already have feedback between parse selection and
word sense


Parses are chosen to reinforce existing patterns of concepts


Now higher level ontological categories can feedback
into the grouping of concepts


Ex. Concept of mammal needed to split “dolphin” from “tuna”


Feedback between parse, word sense and ontological
levels for global consensus on meaning

Ontologies Problematic


MICCE will approximate most likely
(highest mutual information) ontology


BUT, analysts want their own ontologies


Different experts look at same data


At INSCOM


Data stored in primitive entities and paths


MICCE to make semantic model on the fly
tailored to ontology of who is looking at it.

Hypothesis Driven

AND Data Driven


MICCE can flexibly take in analyst input


MICCE can align its ontology to another
with very few points of correspondence


Feedback gives MICCE advantage over
other systems that generate ontologies:


Global consensus


Ability to adapt to any amount of user input

House Of Mirrors Design Pattern


In this design pattern, every thing is defined by
everything else


In MICCE, every concept is defined by its
relation with every other concept


Houses of mirrors use self fulfilling prophecy:
they are highly seedable


If an analyst groups concepts:


Collocated paths found


These help develop analyst’s concept


More consonant concepts and paths found


RELATIVELY FEW points of correspondence needed



Nonlinguistic world: Abstractions of
processes


In text, MICCE separates different roles in
the same person and different abstract
processes that apply to these roles


Applied to the non
-
linguistic world, it will
find different function in the same items,
abstracting on the different processes
performed


These processes can be abstracted and
specify simulations

MICCES align ontologies with each
other


2 MICCES, one in the linguistic and the other in
the nonlinguistic realm, may be aligned through
very few points of correspondence “pointing to
ball and saying ball”


They perform collocations for each other, ie,
images of cats serving to collocate the words
“kitty” and “cat”


Where there are no points of correspondence,
both would fill in the gaps in consonance with
the other

Simulacra


A proposed coevolving simulation system,
which is also a house of mirrors, can be used to
perform the more complicated collocations


By adapting to the seeds of both MICCES, it
helps to fuse the data


Simulacra will accept the systems that both
MICCES extract, and translate them into a a
“language of process” , like a language of
thought


Our approach to natural language
understanding: To Understand is to Simulate