A Cognitive Substrate for Human-Level Intelligence

1
A Cognitive Substrate for Human-Level Intelligence

• Nick Cassimatis
• In collaboration with
• Paul Bello, Magda Bugajska, Arthi Murugesan
• Human-Level Intelligence Laboratory

2

• N.L. Cassimatis (2006). A Cognitive Substrate
  for Human-Level Intelligence. AI Magazine.
  Volume 27 Number 2.

3
General and Human-Level Intelligence

• General Intelligence
• Human-level Intelligence is a useful proxy for
  this.
• It is a useful lower bound on what you can aim
  for.
• If you humans can do X (e.g., use natural
  language), then I am confident a computer can do
  X. If humans cannot do X (e.g., find prime
  factors of million-bit numbers), I am less
  confident.
• Humans are the most general intelligence we know
  of, so you can learn a lot about observing us
  (including introspection.)
• Thinking exactly like a human is not a hard
  constraint

4
Obstacles Profusion and Integration

• Profusion of knowledge.
• Profusion of algorithms.
• Difficulty of integrating it all.

5
Great amount and variety of knowledge
6
Great amount and variety of knowledge

• Even very simple situations can require a much
  knowledge.
• Knowledge about a piggy banks (Charniak)
• It is used to store money.
• If you shake it and there is no sound, it is
  empty.
• You can remove money by breaking it.
• You can remove money by turning it upside down
  and shaking it.
• The more money you put in, the more you get out.
• (dozens more pieces of knowledge).
• Exceptions to each point.
• Cyc Millions of assertions, nowhere near
  complete.
• How do we get all this into one computer program?

7
Diversity of algorithms

• E.g., Natural language conversation
• Vision for recognizing faces, tracking eyes,
  gestures.
• PCA, Bayesian networks, Kalman filters.
• Acoustic speech recognition.
• Hidden Markov Models, Fourier Transforms.
• Syntax, phonology, morphology
• Search- or table-based parsers, rules,
  statistical N-gram models.
• Semantics and Pragmatics (including semantics and
  pragmatics)
• Almost everything.
• There are often dozens or hundreds of variations
  within each algorithmic class.

8
Integration

• How do you get all these algorithms and data
  structures to work with each other
• Procedural integration Bayes nets, logic theorem
  provers, case-based reasoning, neural networks
  ?
• Knowledge integration Scripts, frames, logical
  propositions, patterns of activation ?

9
Learning

• Commits you to weak representations and execution
  algorithms because these are easier to prove
  theorems about and be general.
• You need rich conceptual foundation to do
  learning in the first place.

10
How do we deal with this?

• Profusion Cognitive Substrate
• Integration Polyscheme

11
Cognitive substrate

• Small set of reasoning mechanisms can underlie
  the whole range of human cognition.
• Preliminary guess at what would be a good
  substrate
• Time, space, causality, identity, events,
  parthood, desire.
• Hypothesis Once you have implemented a
  substrate, the rest of AI is relatively simple.
• Substrate is AI-complete.

12
Evidence for substrate

• Personal experience.
• Linguistics.
• Psychology.
• Neuroscience.
• AI.
• Evolution and learning

13
Evolution

• We evolved to deal with a relatively immediate
  and concrete physical and social world, not to
• Contemplate life on Mars.
• Trade stock options.
• Explore number theory.
• Design airplanes.
• Repair speed boats.
• Calculate tips.
• Market insurance policies.
• Etc.
• Whatever mechanisms we use to reason about these
  were originally designed to deal with the
  physical and social world.
• Hence, human social and physical reasoning
  mechanisms are sufficient for the full array of
  human reasoning.

14
Learning

• What is it that kids have that give them the
  ability to learn so much, to be so general?
• Substrate mechanisms.
• Mechanism for mapping.
• Mechanisms for learning.
• Mechanisms for being taught.

15
Substrate research

• Overall approach
• Build substrate (2-4 year old?)
• Turn it loose on the world.
• Building the substrate
• First guess (physical reasoning)
• Map onto several domains (epistemic reasoning,
  syntax, word learning)
• Each mapping leads to refinements and
  generalizations
• Learning mechanisms (analogy)

16
Contrast

• Many people dream of building a baby and setting
  it loose on the world.
• Contrast
• Need a richer substrate.
• Need to integrate learning with reasoning.

17
Building a substrate

• Reasoning about time, space, causality, identity,
  events, parthood, desire
• Requires integration of temporal, spatial, causal
  data structures and algorithms.
• Polyscheme is an approach to this problem.

18
Common Functions

• Basic functions
• Forward inference.
• Subgoaling.
• Identity matching.
• Representing alternate worlds.
• Basic functions can be computed using different
  representations
• E.g., subgoaling
• Logic when B ?H and want to know if H, make a
  subgoal of B.
• Neural Network To know the value of the output
  units, make a goal of the input units.
• Perception To know what is at P, point the
  camera to P.

19
AI algorithms are ways of ordering common
functions

• Counterfactual reasoning
• When uncertain about A, simulate the world where
  A and simulate the world where not-A.
• Backtracking search
• Nested counterfactual reasoning.
• Stochastic simulation
• When you think A is more likely than not-A,
  simulate the world where A is true more often
  than the world where A is not true.
• Logic-theorem proving
• When uncertain about P
• Ground P if you can.
• Subgoal on P if you can.
• Means-ends planning.
• When you want G, and A achieves G,
• Simulate the world where A is true and subgoal on
  A.

20
Integration of algorithms
21
Integration of representations
22
Physical reasoner demonstrates flexible
integration

• Reactive/Deliberative Robot architecture
• Combines means-ends planning, logical inference,
  production rules, neural networks, truth
  maintenance, reactive subsystem etc.
• Promising approach to (hard) substrate problems.
• In physical reasoner.
• Adding algorithms and representations adds to
  huge increase in efficiency.
• Several problems mapped onto physical reasoning
  substrate.

N. L. Cassimatis, J. Trafton, M. Bugajska, A.
Schultz (2004). Integrating Cognition, Perception
and Action through Mental Simulation in Robots.
Journal of Robotics and Autonomous Systems.
Volume 49, Issues 1-2, 30 November 2004, Pages
13-23.
23
Example Syntax

• Murugesan, N.L. Cassimatis (2006). A Model of
  Syntactic Parsing Based on Domain-General
  Cognitive Mechanisms. In Proceedings of 28th
  Annual Conference of the Cognitive Science
  Society.
• N. L. Cassimatis (2004). Grammatical Processing
  Using the Mechanisms of Physical Inferences. In
  Proceedings of the Twentieth-Sixth Annual
  Conference of the Cognitive Science Society.
• Show how to map syntactic parsing to physical
  reasoning.
• What could words, phrases, case, empty
  categories, traces, long-distance dependencies,
  coreference, subjacency, anaphora, etc. have to
  do with gravity and collision?
• If these two domains have underlying unity, then
  you cannot quickly rule out mappings between
  other domains.

24
Syntax
Verbal World Physical World
World, phrase, sentence Event
Constituency Parthood
Phrase structure constraints Physical constraints
Word/phrase category Categories
Word/phrase order Temporal order
Phrase attachment Event identity
Coreference/binding Object identity
Traces Object permanence
Short- and long-distance dependencies Apparent motion and long paths.
25
Syntax
26
Word Learning

• One-shot, non-associative word learning
• M. Bugajska, N.L. Cassimatis (2006). Beyond
  Association Social Cognition in Word Learning.
  In Proceedings of the International Conference on
  Development and Learning.

27
Theory of Mind

• Use counterfactual and default reasoning
  mechanisms to reason about other peoples
  beliefs.
• P. Bello N.L. Cassimatis (2006). Developmental
  Accounts of Theory-of-Mind Acquisition
  Achieving Clarity via Computational Cognitive
  Modeling. In Proceedings of 28th Annual
  Conference of the Cognitive Science Society.
• P. Bello N.L. Cassimatis (2006). Understanding
  other Minds A Cognitive Modeling Approach. In
  Proceedings of the 7th International Conference
  on Cognitive Modeling.

28
Summary of progress

• Preliminary implementation (physical reasoning)
• Demonstrates Polyscheme enables advance in
  flexibility, integration and power of intelligent
  systems.
• Manually mapped onto several domains (epistemic
  reasoning, syntax, word learning, wargaming)
• Each mapping demonstrates the plausibility of the
  substrate appraoch.
• Each mapping leads to refinements,
  generalizations and eliminations about the
  substrate.
• Learning mechanisms (analogy).
• Just starting
• Teaching the substrate (this will gradually
  result from our NLP work).

29
What this demonstrates

• Cognitive substrate enables a real advance
  towards solving the profusion and integration
  problem.
• It enables qualitative advances in capabilities
  of intelligent systems.
• It enables faster development of systems.

30
Future work

• Keep doing mappings.
• Pragmatics.
• Metacognition.
• Self-awareness, consciousness.
• Use insights from this to enhance substrate.
• Automate mappings.
• Keep driving this process towards the goal of
  having a 2-4 year old intelligence that can learn
  from interacting with the world and people.

31
How people can help

• Software engineering.
• Find a domain and do a mapping.
• Add an algorithm or subdomain to the substrate.