A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol....

21
A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (200 6) Summarized by Eun Seok Lee BI. 2008. 04. 07.

description

The Procedural Profusion Problem A human utterance hidden Markov models Convert continuous acoustic signal into discrete representation of the phonemes, morphemes, and words chart- or search-based algorithms Identify the syntactic structure logical, case-based, and probabilistic methods Reasoning about the world and other people’s intention

Transcript of A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol....

Page 1: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

A Cognitive Substrate for Achieving Human-Level

IntelligenceNicholas L. Cassimatis

AI Magazine Vol. 27, No. 2 (2006)

Summarized by Eun Seok LeeBI. 2008. 04. 07.

Page 2: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

A Profusion Problem• “When is the first Pittsburgh Steelers game after (the World Series, T

hanksgiving, my daughter’s birthday, the next full moon)?”• Cf. Cyc (Lenat and Guha 1990) & ThoughtTreasure (Mueller 1998) –

not yet to provide a comprehensive store of all the knowledge for such queries.

Question

knowledge info

National holidays

User info Celestial movements

Page 3: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

The Procedural Profusion Problem

A human utterance

hidden Markov models

Convert continuous acoustic signal into discrete representation of the phonemes, morphemes, and words

chart- or search-based algorithms

Identify the syntactic structure

logical, case-based, and probabilistic methods

Reasoning about the world and other people’s intention

Page 4: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

The Procedural Profusion Problem

• Too many computational problems involved with difficult-to-integrate methods.

• Each aspects can best be dealt with different methods• Tanenhaus and Trueswell 1995 – Above is very difficult problem – on

ly multiply for systems that integrate more of human-level intelligence.

• Then what about enabling computers automatically storing and collecting knowledge and algorithms? – not sufficient; only learn to delegate among existing algorithms.

• And, control and data structures of these different classes of algorithms are very difficult to integrate

• Thus, the profusion problem is a genuinely difficult integration problem.

Page 5: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

The Cognitive Substrate Hypothesis

• Human’s earlier cognitive mechanism with adapting mechanism is sufficient to achieve human-level intelligence in all domains.

• A relative small set of computational problems that once solved, (“cognitive substrate,”) can be adapted to solve other problems.

Page 6: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

An Example of a ‘Cognitive Substrate’Basic social, physical reasoning problem

Reasoning

Temporal intervals

Causal relations

Desire

Objects

EventsBelief

Ontologies

“Cognitive substrate” – A set of computational mechanisms

i.e. “Once a set of ‘cognitive substrate’ is constructed, the rest will be relatively easy.”

Page 7: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

The Benefits of the Cognitive Substrate Hypothesis

1. Smaller problem2. Quicker intelligent system development3. Easier integration across domains

• If cognitive substrate underlie cognition in most domains of human cognition, then much of the problem of human-level cognition becomes more tractable.

• AI, Cognitive psychology, linguistics, neuroscience support the cognitive substrate hypothesis.

Page 8: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Implicit Substrate Hypothesis in Much AI Research

• Representative research: – Search through a state space (Newell and

Simon 1972)– Updating probabilities in a Bayesian network

(Pearl 1988)– A modest set of primitives that can represent

much of the semantics of human language (Shank 1975) – not implemented because reasoning problems with these primitives are not yet achieved.

– Thus require benefits of each specific class of AI methods should be integrated into one system.

Page 9: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Linguistic Semantics• Jackendoff – structures used to represent the semantics

of a relatively small set of semantic fields can be used to represent the semantics of many other semantic fields.

• i.e. primitives such as cause, go, path, to, from are common in other frameworks.

• The formalization:– “John entered the room.” -> GO (John, [path [to: room]])– “John left the room.” -> GO (John, [path [from: room]])

• Large set of word classes with only a few more primitives – support the notion that a relatively small set of mechanisms can lead to human-level intelligence in all domains.

Page 10: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Cognitive Psychology and Neuroscience

• Much nonspatial or physical thought involves mechanisms which are for spatial and physical ones.

• Barsalou et al (2003) – human mapping visual and motor representations onto abstract, nonphysical concepts

• Spivey et al (2001) – associating sitting position with verb ‘push/respect’

• Ricahrdson et al (2003) – harder understanding sentences of certain combination of images and words.

• Warington et al (1984) – visual and motor regions activation during nonperceptual cognition

Page 11: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Constituents of Cognitive Substrates

• Cassimatis 2002 – preliminary lists includes reasoning about time, space, part-hood, categories, causation, uncertainty, belief, desire.

• Implied research program– 1) identify and implement a cognitive substrate– 2) find mappings from multiple domains onto the cogn

itive substrate– 3) automate the process of adapting a cognitive subst

rate so that it can solve problems in other domains

Page 12: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Implementing a Cognitive Substrate

• Polyscheme cognitive architecture: – enables multiple computational methods to be implem

ented much more ubiquitous.

• Two principles: – CFP common function principle– MIP multiple implementation principle

• Attention Fixation – Very different algorithms can all be reformulated in ter

ms of sequences of attention fixations

Page 13: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Common Functions• Forward inference. • Subgoaling. • Simulate alternate worlds. • Identity matching.

• i.e.implemeting an algorithms– Search. “When uncertain about whether A is true, represent the w

orld where A is true, perform forward inference, represent the world where A is not true, perform forward inference. If forward inference leads to further uncertainty, repeat.”

– Stochastic simulation. “When A is more likely than not-A, represent the world where A is true and perform forward inference in it more often than you do for the world where not-A is true.”

Page 14: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

MIP for forward inference• Neural Networks.

– The activation of input units of a feedforward neural network leads to a change in the activation of the output units of the network.

– Rrepresent facts that can be inferred from the facts represented by the input units.

• Forward rule changing. – Production systems can be constructed to match the left-hand sides of p

roduction rules against a set of currently known facts to infer new facts represented by the right hand sides of rules.

• Ontologies. – When an object, o, is a member of category C in a category hierarchy, on

e can infer that o is a member of C1 … Cn, the ancestors of C.

Page 15: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Implementing an algorithm

A CFP

Subgoaling

Simulate alternate worlds

Search

Stochastic simulationIdentity

matching

Forward inference

Algorithms

Neural Networks

Forward Rule Chaining

Ontologies An MFP

Page 16: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Attention Fixation• Very different algorithms

– can all be reformulated in terms of sequences of attention fixations

• Inference algorithms (originally based on very different computational formalisms): – can be executed as sequences of a small set of

common functions (according to the CFP) that can be easily interleaved

– and that these common functions can be implemented using many different algorithms (according to the MIP)

Page 17: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.
Page 18: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Leveraging a Cognitive Substrate

• How a substrate on a Polyscheme model of human physical reasoning used to construct a natural language parser?

• Many grammatical structures have analogues to nonlinguistic cognitive structures.

• Formalism: – Events (e), Objects (o), Places (p)– Category(e, MotionEvent), Agent(e, x), Origin(e, p1),

Destination(e, p2), Occurs(e, t) – An unsupported object falls is:

• Location(o, p1, t1) + Below(p2, p1) + Empty(p2, t1)• Category(e, MotionEvent) + Origin(e, p1) + Destination(e, p2) + Occu

rs(e, t2) + Meets(t1, t2).

Page 19: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Leveraging a Cognitive Substrate

• Utterances are events: Category(e, dog-utterance), Occurs(e, t).

• Word order is temporal order: Category(e1, JohnUtterance), Occurs(e1, t1) Category(e2, BitUtterance), Occurs(e2, t2)Meets(t1, t2)…

• Physical and linguistic events both belong to categories organized hierarchically– Constituency is a parthood relation.– Coreference and binding are object-identity relationships.– Phrase attachment is an event identity relationship.

Page 20: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.
Page 21: A Cognitive Substrate for Achieving Human-Level Intelligence Nicholas L. Cassimatis AI Magazine Vol. 27, No. 2 (2006) Summarized by Eun Seok Lee BI. 2008.

Conclusion: Benefits of Cognitive Substrates

1. Much easier to create an intelligent system for new domains

2. Much easier integration among domains

3. The problem of achieving human-level AI is reduced and simplified by mapping a relatively small set of problems onto a substrate