39
FUSION OF LANGUAGE AND THOUGHT PROCESSES FOR CTS Leonid Perlovsky Technical Advisor, AFRL Collaborative Technologies and Systems Conference 2003, Orlando, Florida

FUSION OF LANGUAGE AND THOUGHT PROCESSES FOR CTS

Embed Size (px)

DESCRIPTION

FUSION OF LANGUAGE AND THOUGHT PROCESSES FOR CTS. Collaborative Technologies and Systems Conference 2003, Orlando, Florida. Leonid Perlovsky Technical Advisor, AFRL. CTS AND INTELLIGENT AGENTS. Collaborative systems include multiple interacting intelligent agents - PowerPoint PPT Presentation

Citation preview

Page 1: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

FUSION OF LANGUAGE AND THOUGHT

PROCESSES FOR CTS

Leonid PerlovskyTechnical Advisor, AFRL

Collaborative Technologies and Systems Conference 2003, Orlando,

Florida

Page 2: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

CTS AND INTELLIGENT AGENTS

Collaborative systems include multiple interacting intelligent agents– a human, machine, device or software code

Agents are– significantly autonomous and goal-oriented, perform

various functions, and communicate with other agents– equipped with sensors or collect data, receive

communications, extracts information – use existing knowledge, integrate new information into

producing new knowledge, send communications– embody the concept of life and intelligence

What are the required intelligent agent technologies?

Page 3: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

INTELLIGENT AGENT TECHNOLOGIES

Interfaces and access– man-machine and machine-machine interfaces– knowledge and data access

Understanding of– language, situations, and environment

Fusion – knowledge and data from diverse sources and disciplines,

Decision making – heterogeneous environment, with inaccurate data,

uncertain knowledge and intuitions– information exchange, knowledge management

Abilities for thinking and language– a mysterious territory

Page 4: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

LANGUAGE AND THINKINGPAST

Artificial Intelligence, 1950s-1980s– logical rules– no principal difference between thinking and language– failed, yet no replacements to logic when combining L. & T.

Linguistics– Chomskyan linguistics, computational linguistics, cognitive

linguistics: relate words to words– No relation to surrounding world

Closely related and intertwined evolution in human mind– science cannot tell us yet what is language without thinking

or v.v.

Page 5: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

LANGUAGE AND THINKINGFUTURE

Thinking and understanding– identify “concepts” of objects, relationships and situation

in sensory data– relate concepts to needs and emotions– relate concepts to behavior

Language is a part of mind– involved in concepts, emotions, instincts– closest to concepts– words are combined into phrases like retinal signals are

combined into objects (?)

Where language and thoughts come together?– Concepts? Not logical rules and artificial intelligence

again?

Page 6: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

PHYSICS AND MATHEMATICS OF MINDRANGE OF CONCEPTS

Logic is sufficient to explain mind– [Newell, “Artificial Intelligence”]

No new specific mathematical concepts are needed– Mind is a collection of ad-hoc principles, [Minsky]

Specific mathematical constructs describe the multiplicity of mind phenomena– “first physical principles of mind”– [Grossberg, Zadeh, Perlovsky,…]

Quantum computation– [Hameroff, Penrose, Perlovsky,…]

New unknown yet physical phenomena– [Josephson, Penrose]

Page 7: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

GENETIC ARGUMENTSFOR THE “FIRST PRINCIPLES”

There is about 30,000 genes in human genome– relate concepts to needs

Only about 2% difference between human and apes

Say, 1% difference between human and ape minds– Only about 300 proteins

It is likely, that few general principles of concept learning are required to explain our ability to operate with concepts– If we count “a protein per concept”– If we count combinations: 300300 ~ unlimited => all

languages could have been genetically h/w-ed (!?!)

Languages are not genetically hardwired– Because they have to be flexible and adaptive

Page 8: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

INFORMATION PROCESSING AND UNDERSTANDING

Understanding the meaning of signals (visual, acoustic, text)– Identify objects in signals

• signals -> concepts; or words -> phrases

– Associate relevant objects• objects -> scenes; or phrases -> more general concepts

In this task the human mind is by far superior qualitatively to existing mathematical methods– Effort has been devoted toward incorporating “biological

lessons” into smart algorithms, yet success has been limited

– Why is this so and how to overcome existing limitations?

Page 9: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

REASONS FOR PAST LIMITATIONS

The basis of human intelligence is in combining conceptual understanding with emotional evaluation– became exceedingly well appreciated among psychologists and

neurobiologists during the last ten years – human understanding without emotional involvement is basically

flawed [Damasio]

This new understanding has not been accepted by mathematical and engineering community – mathematical laws governing emotional involvement into thinking

process have not been well known – there is a long-standing cultural belief that emotions are opposite

to thinking and intellectually inferior • Socrates, Plato, Aristotle• reiterated by founders of Artificial Intelligence [Newell]

Page 10: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

FUNDAMENTAL MATHEMATICAL PROBLEM

Combinatorial Complexity (CC): – understanding involves evaluating a large number

of combinations– words into sentences, pixels or samples into

objects, objects into scenes– a general problem of all data association methods

CC was encountered for over 50 years– statistical pattern recognition and neural

networks: CC of learning requirements – rule-based systems, expert systems, and AI, in the

presence of variability: CC of rules– model-based systems, utilizing adaptive models:

CC of computations (N and NP complete)– Chomskyan linguistics: (1-1957) rule-based, (2-

1981) model-based (rules and parameters)

Page 11: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

CC AND TYPES OF LOGIC

CC is related to formal logic– law of excluded third

• every logical statement is either true or false

– there could be no similarity/distance measure between logical statements

– CC is Godel’s “incompletenes” in a finite system

Multivalued and fuzzy logic eliminated the “law of excluded third”– yet, they are based on the math. of formal logic– e.g. fuzzy logic systems are either too fuzzy or too crisp

A similarity measure between logical statements was not introduced

Page 12: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

STRUCTURE OF MIND

Concepts – Models of objects, their relations, and situations– Evolved to satisfy instincts

Instincts– Internal sensors (e.g. sugar level in blood)

Emotions– Neural signals connecting instincts and concepts

• e.g. a hungry person sees food all around

Behavior– Models of goals (desires) and muscle-movement

Hierarchy– Concept-models and behavior-models are organized in a “loose”

hierarchy

Page 13: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

SIMILARITY MEASURE AND DYNAMIC LOGIC

A similarity measure– based on a similarity between models and data (words)

• equivalent to emotional evaluative signals

– leads to dynamics (equations of motions) improving concept-models by maximizing similarity (dynamic logic)

Dynamic Logic unifies formal and fuzzy logic– initial “fuzzy model-concept” dynamically evolve into

“formal-logic or crisp model-concept”

Overcomes CC of model-based recognition – fast algorithms

• low-polynomial M*N, instead of combinatorial MN

– associates pixels into objects (or words into phrase-models) without CC

Page 14: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

THINKING

Understanding and learning – Model-concepts always have to be adapted to incoming

signals or data• lighting, surrounding, new objects and situations

Instinct for knowledge and understanding– Models-concepts are adapted and improved even when

there is no concrete “bodily” needs– Increase similarity between models and world

Emotions related to knowledge instinct– Satisfaction or dissatisfaction

• change in similarity between models and world

– Harmony or disharmony: aesthetic emotion

Behavior related to knowledge– Adaptation and learning of concepts (behavior in the mind)

Page 15: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MODELING FIELD THEORY basic two-layer hierarchy: from signals to objects

Signals and Concept-Models– signals x(n), n = 1,…,N

– model-object Mm(Sm,n), parameters Sm, m = 1, …;

Goal: learn object-models and understand signals– associate samples n with models m and find parameters Sm

– learn signal-contents of objects (and object properties)

Maximize similarity, between signals and models, L– knowledge instinct– Likelihood or mutual information, L = l({x}) = l(x(n))

– l(x(n)) = r(m) l(x(n) | Mm(Sm,n)) (M may depend on n)

– CC: L contains MN items: all associations of words and models

n

m

Page 16: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

DYNAMIC LOGIC ALGORITHM (DLA) (non-combinatorial solution)

Start with a set of signals and unknown object-models– any parameter values Sm – associate fuzzy object-model with its contents (signal composition)– (1) f(m|n) = r(m) l(n|m) / r(m') l(n|m')

Improve parameter estimation– (2) Sm = (1- ) Sm + f(m|n) [ll(n|m)/Mm]*[Mm/Sm]

• ( determines speed of convergence)

– learn signal-contents of objects

Continue iterations (1)-(2). Theorem: MFT is converging - similarity increases on each iteration- aesthetic emotion is positive during learning

Each concept-model is an agent– semi-independent, interacting with other agents

• competing for evidence (among signals)

– learning its properties and recognizing its signals

'm

n

Page 17: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

LINGUISTICSWORDS, CONCEPTS AND GOALS

Text is a (loose) hierarchy of concepts – Word is a concept; it acquires meaning in a phrase– Phrase-concept acquires meaning in a “paragraph”,…

Model-concepts (e.g. phrases made up of words)– Simplistic “bag”-model

• a set or collection of words

– More complex models: word order and relationships– Real-language models

• grammar (Chomsky, Pinker, Jackendoff, Rieger, Mehler…)

Goal-instinct– A search engine: find conceptual similarity between a query and

text• analyze both in terms of concepts

– Learn and identify model-concepts in texts (language instinct = knowledge instinct)

Page 18: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MODELING FIELD THEORY basic two-layer hierarchy: words and phrase-concepts

Words and Concept-Models– words w(n), n = 1,…,N

– model-phrase Mm(Sm,n), parameters Sm, m = 1, …;

– Simplistic “bag”-model: Mm = Sm = {w}m

Goal: learn phrase-models– associate words n with models m and find parameters Sm

– learn word-contents of phrases (and grammatical relationships)

Maximize similarity, between words and models, L– language instinct = knowledge instinct– Likelihood or mutual information, L = l({w}) = l(w(n))

– l(w(n)) = r(m) l(w(n) | Mm(Sm,n)) (M may depend on n)

– CC: L contains MN items: all associations of words and models

n

m

Page 19: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

DYNAMIC LOGIC ALGORITHM (DLA) (non-combinatorial solution)

Start with a large body of text and unknown phrase-models– any parameter values Sm – associate fuzzy phrase-model with its contents (words)– (1) f(m|n) = r(m) l(n|m) / r(m') l(n|m')

Improve parameter estimation– (2) Sm = (1- ) Sm + f(m|n) [ll(n|m)/Mm]*[Mm/Sm]

• ( determines speed of convergence)

– learn word-contents of phrases (and grammatical relationships)

Continue iterations (1)-(2). Theorem: MFT is converging - similarity increases on each iteration- aesthetic emotion is positive during learning

Each phrase-concept-model is an agent– semi-independent, interacting with other agents

• competing for evidence (among words)

– learning its properties and recognizing its words

'm

n

Page 20: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

CATCH ME BY HAND

If I give you enough time you’ll be able to catch me on the previous slide – the “bag”-model is non-differentiable

– this is a principal moment, learning non-differentiable models requires sorting through combinations

– lead to combinatorial complexity

– differentiable models can be defined with a little trick

Page 21: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

INTEGRATEDLANGUAGE AND THINKING

Where language and thoughts come together?– concept-models have linguistic and objective aspects– a fuzzy concept m has sensory and linguistic model

• Mm = { Mmsensory,Mm

linguistic };

– language and thoughts are fused at fuzzy pre-conscious level• before concepts are learned

Understanding language and sensory data– baby learning: “look, this is a car”– each linguistic model has an empty “slot” for objects and

situations in surrounding world– each sensory or situational model has an empty “slot” for a word

or phrase– language participates in thinking and v.v.

Two types of information help learning and understanding each other – help associating signals, words, models, and behavior

Page 22: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

INNER LINGUISTIC FORM HUMBOLDT, the 1830s

In the 1830s Humboldt discussed two types of linguistic forms– words’ outer linguistic form (sounds) – a formal designation– and inner linguistic form (???) – creative, full of potential

This remained a mystery for rule-based AI, structural linguistics, Chomskyan linguistics– rule-based approaches using the mathematics of logic make

no difference between formal and creative

In MFT and DLA there is a difference – static form of learned (converged) concept-models– dynamic form of fuzzy concepts, with creative learning

potential and emotional content

Page 23: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

WHY MIND AND EMOTIONS?

A lot about the mind can be explained: concepts, instincts, emotions, conscious and unconscious, intuition, aesthetic ability,…– but, isn’t it sufficient to solve mathematical equations or to code a

computer and execute the code?

A simple yet profound question– the answer is in history and practice of science– Newton laws do not contain all of the classical mechanics– Maxwell equations do not exhaust radars and radio-communication– a physical intuition about the system is needed – an intuition about MFT was derived from biological, linguistic,

cognitive, neuro-physiological, and psychological insights into human mind

Practical engineering applications of DLA require biological, linguistic, cognitive, neuro-physiological, and psychological insights in addition to mathematics

Page 24: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT THEORY OF MIND

MFT dynamics: elementary thought process– a large number of model-concepts compete for incoming signals – uncertainty in models corresponds to uncertainty in associations f(m|n)– eventually, one model (m') wins a competition for a subset {n'} of input

signals w(n), when parameter values match object properties, and f(m'|n) values become close to 1 for n{n'} and 0 for n{n'}

– upon convergence, the entire set of input signals {n} is divided into subsets, each associated with one model-object

– fuzzy a priori concepts (unconscious) become crisp concepts (conscious) • dynamic logic

Elementary thought process, consciousness and unconscious– Aristotle: in thinking, an a priori form-as-potentiality (fuzzy model) meets

matter (signals) and becomes a form-as-actuality (a concept)– Jung: conscious concepts are developed by mind based on inherited

structures of mind, archetypes, inaccessible to consciousness– Grossberg: models attaining a resonant state (winning the competition for

signals and becoming crisp in this process) reach consciousness

Page 25: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT THEORY OF MIND -understanding-

Incoming signals, {x,w} are associated with model-concepts (m)– creating phenomena (of the MFT-mind), which are understood as objects, situations,

phrases,…– in other words signal subsets acquire meaning (e.g., a subset of retinal signals

acquires a meaning of a chair)

Several aspects of understanding and meaning– concept-models are connected (by emotional signals) to instincts and to behavioral

models that can make use of them for satisfaction of bodily instincts– an object is understood in the context of a more general situation in the next layer

consisting of more general concept-models (satisfaction of knowledge instinct)• each recognized concept-model (phenomenon) sends (in neural terminology: activates) an

output signal• a set of these signals comprises input signals for the next layer models, which ‘cognize’

more general concept-models• this process continues up and up the hierarchy towards the most general models: models of

universe (scientific theories), models of self (psychological concepts), models of meaning of existence (philosophical concepts), models of a priori transcendent intelligent subject (theological concepts)

– neural brain organization: individual modules, which form approximate hierarchies, along with a number of “parallel” and “loop-like” pathways

Page 26: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

SIGNS AND SYMBOLSmathematical semiotics

Signs: stand for something else– non-adaptive entities (mathematics, AI)– brain signals insensitive to context (Pribram)

Symbols– signs (mathematics, AI)– psychological processes connecting conscious

and unconscious (Jung)– brain signals sensitive to context (Pribram)– processes of sign interpretation

Mathematics of symbol-processes– relationships to thinking– relationships to language

Page 27: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT THEORY OF SYMBOLS -mathematical semiotics-

Semiotics studies symbol-content of culture

Example: consider a written word "chair" – It can be interpreted by mind to refer to something else: an entity in the

world, a specific chair, or the concept "chair" in the mind– In this process, the mind, or an intelligent system is called an interpreter,

the written word is called a sign, the real-world chair is called a designatum, and the concept in the interpreter's mind, the internal representation of the results of interpretation is called an interpretant of the sign

– The essence of a sign is that it can be interpreted by an interpreter to refer to something else, a designatum

This is a simplified description of a thinking process, called semiosis– its mechanism is given by the elementary thought process

Elementary thought process involving consciousness and unconscious, concepts and emotions, is a dynamic symbol process – a much more complicated entity than was originally envisioned by founders

of “symbolic AI”

Page 28: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT THEORY OF MIND - aesthetic emotions and beauty -

Aesthetic emotions (not related to bodily satisfaction)– Instincts for knowledge and language (learning concept-models) – Emotions (satisfaction-dissatisfaction): harmony-disharmony– Maximize similarity between models and world

• between our understanding of how things ought to be and how they actually are in the surrounding world; Kant: aesthetic emotions

Beauty– Harmony is an elementary aesthetic emotion; higher aesthetic emotions

• development of more complex “higher” models

– The highest forms of aesthetic emotion, beauty • related to the most general and most important models• models of the meaning of our existence, of our purposiveness or intentionality• beautiful object stimulates improvement of the highest models of meaning

– Beautiful “reminds” us of our purposiveness• Kant called beauty “aimless purposiveness”: not related to bodily purposes• he was dissatisfied by not being able to give a positive definition

– knowledge instinct

• absence of positive definition remained a major source of confusion in philosophical aesthetics till this very day

Page 29: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT THEORY OF MIND - physical intuition -

Intuitive perception (imagination) of object-models and their relationships with objects in the world– involves fuzzy unconscious concept-models

– in process of being learned and adapted • toward crisp and conscious models, a theory

– such models satisfy or dissatisfy the knowledge instinct before they are accessible to consciousness, hence the complex emotional feel of an intuition

Beauty of a physical theory discussed often by physicists – related to satisfying our feeling of purpose in the world

– satisfying our need to improve the models of the meaning in our understanding of the universe

Page 30: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

REAL WORLD APPLICATIONS

Many applications have been developed– Government– Medical– Commercial

Sensor signals processing and object recognition– Variety of sensors

Internet search engines– Based on text understanding

Financial market predictions– Market crash on 9/11 predicted a week ahead

Page 31: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

BACK UP

MFT and Buddhism

MFT vs. biology

Classical methodology flowchart

MFT flowchart

MFT vs. inverse problems

MFT predictions and testing

MFT future directions

Publications

Page 32: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT AND BUDDHISM

Fundamental Buddhist notion of “Maya” – the world of phenomena, “Maya”, is meaningless deception

– penetrates into the depths of perception and cognition

– phenomena are not identical to things-in-themselves

Fundamental Buddhist notion of “Emptiness” – “consciousness of bodhisattva wonders at perception of emptiness

in any object” (Dalai Lama 1993)

– any object is first of all a phenomenon accessible to cognition

– value of any object for satisfying the “lower” bodily instincts is much less than its value for satisfying higher needs, knowledge instinct

– Bodhisattva’s consciousness is directed by knowledge instinct

– concentration on “emptiness” does not mean emotional emptiness, but the opposite, the fullness with highest emotions related to the knowledge instinct, beauty and spiritually sublime

Page 33: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT vs. BIOLOGY OF EYE

 Human eye is part of the brain - Integrated sensor-processor system in both design and in operations

• multi-layer hierarchical system• integrated adaptive optimized resource allocation

- Feedback from higher layers to lower layers is essential • eye-brain neural pathway contains more feedback connections than feedforward ones

 Adaptive, joint optimization of sensor-processor system network - Based on a hierarchy with feedback among layers and modules- What is the nature of this feedback?

 MFT hierarchy with feedback - Every layer has 5 basic modules/elements: (1) incoming signals (structured at lower layer, unstructured at the current layer) (2) models: phenomenology (emissivity, geometry) and simulation codes (3) similarity measure between signals and models(4) adaptation mechanism(5) outgoing signals (a structure: sign-concept)

Page 34: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

CLASSICAL METHODOLGY

Result: Conceptual objects

signals Input: World/sceneSensors / Effectors

MODELS/templates•objects, sensors•physical models

Recognition

Page 35: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFTbasic two-layer hierarchy: signals and concepts

Result: Conceptual objects

signals

Input: World/scene

Sensors / Effectors

Correspondence / Similarity measures

MODELS•objects, sensors•physical models

Attention / Actionsignals Sim.signals

Page 36: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT VS. INVERSE SCATTERING

Inverse Scattering in Physics– reconstruction of target properties by “propagating back” scattered fields

– usually complicated, ill-posed problems (exception: CATSCAN)

Biological systems (mind) solve this problem all the time– by utilizing prior information (in feedback neural pathways)

Classical Tikhonov’s inversion cannot use knowledge– regularization parameter () is a constant – Morozov’s modification can utilize prior estimate of errors for

Inverse Scattering using MFT– can utilize any prior knowledge ( became an operator)– utilizes prior knowledge adaptively ( depends on parameters)

Page 37: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT PREDICTIONS AND TESTING

General neural mechanisms of the elementary thought process– confirmed by neural and psychological experiments

– includes neural mechanisms for bottom-up (sensory) signals, top-down (“imagination”) model-signals, and the resonant matching between the two

Adaptive modeling abilities – well studied: adaptive parameters are synaptic connections

Instinctual learning mechanisms – studied in psychology and linguistics

Ongoing and future research will confirm, disprove, or suggest modifications to

– mechanisms of language and thinking integration– mechanisms of model parameterization and parameter adaptation– reduction of fuzziness during learning– similarity measure as a foundation of knowledge and language instincts

Page 38: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

MFT FUTURE DIRECTIONS

Developing MFT models based on known linguistic models

Differentiated forms of knowledge instinct – highly differentiated emotions are involved in human

conversation and human thinking– multiple measures of similarity, differentiated knowledge

instinct• differentiated emotional concepts

Quantum Computing MFT devices

Page 39: FUSION OF  LANGUAGE AND THOUGHT PROCESSES FOR CTS

PUBLICATIONS

OXFORD UNIVERSITY PRESS

www.oup-usa.org