Title: The%20ICSI/Berkeley%20Neural%20Theory%20of%20Language%20Project
1The ICSI/Berkeley Neural Theory of Language
Project
ECG
2Moving from Spatial Relations to Verbs
- Open class vs. closed class
- How do we represent verbs (say of hand motion)
- Can we build models of verbs based on motor
control primitives? - If so, how can models overcome central
limitations of Regiers system? - Inference
- Abstract uses
3Perceptual And Motor Schemas
- A perceptual schema embodies the process
whereby the system determines whether a given
domain of interaction is present in the
environment. - A schema assemblage combines an estimate of
environmental state with a representation of
goals and needs - The internal state is also updated by knowledge
of the state of execution of current plans made
up of motor schemas which are akin to control
systems but distinguished by the fact that they
can be combined to form coordinated control
programs
4Coordination of Pattern Generators
5Coordination
- PATTERN GENERATORS, separate neural networks that
control each limb, can interact in different ways
to produce various gaits. - In ambling (top) the animal must move the fore
and hind leg of one flank in parallel. - Trotting (middle) requires movement of diagonal
limbs (front right and back left, or front left
and back right) in unison. - Galloping (bottom) involves the forelegs, and
then the hind legs, acting together
6Preshaping While Reaching to Grasp
7Hypothetical coordinated control program for
reaching and grasping
Perceptual Schemas
Motor Schemas
Dashed lines activation signals solid lines
transfer of data. (Adapted from Arbib 2004)
8(No Transcript)
9Internal Model and Efference Copy
10(No Transcript)
11Many areas code for motion parameters
12(No Transcript)
13Multiple, chronically implanted, intracranial
microelectrode arrays would be used to sample
the activity of large populations of single
cortical neurons simultaneously. The combined
activity of these neural ensembles would then be
transformed by a mathematical algorithm into
continuous three-dimensional arm-trajectory
signals that would be used to control the
movements of a robotic prosthetic arm. A closed
control loop would be established by providing
the subject with both visual and tactile feedback
signals generated by movement of the robotic arm.
14A New Picture
Rizzolatti et al. 1998
15The fronto-parietal networks
Rizzolatti et al. 1998
16F5 Mirror Neurons
Gallese and Goldman, TICS 1998
17Category Loosening in Mirror Neurons (60)
Observed A is Precision Grip B is Whole Hand
Prehension Action C precision grip D
Whole Hand Prehension
(Gallese et al. Brain 1996)
18PF Mirror Neurons
- Neuron responds to execution (grasping) but to
grasping and releasing in observation. - Mirror neurons in parietal cortex.
- Difference in left hand and right hand.
(Gallese et al. 2002)
19A (Full vision) B (Hidden) C (Mimicking) D
(HiddenMimicking)
Umiltà et al. Neuron 2001
20F5 Audio-Visual Mirror Neurons
Kohler et al. Science (2002)
21Summary of Fronto-Parietal Circuits
- Motor-Premotor/Parietal Circuits
- PMv (F5ab) AIP Circuit
- grasp neurons fire in relation to movements
of hand prehension necessary to grasp object - F4 (PMC) (behind arcuate) VIP Circuit
- transforming peri-personal space coordinates so
can move toward objects - PMv (F5c) PF Circuit F5c
- different mirror circuits for grasping, placing
or manipulating object - Together suggest cognitive representation of the
grasp, active in action imitation and action
recognition
22Evidence in Humans for Mirror, General Purpose,
and Action-Location Neurons Mirror Fadiga et
al. 1995 Grafton et al. 1996 Rizzolatti et al.
1996 Cochin et al. 1998 Decety et al. 1997
Decety and Grèzes 1999 Hari et al. 1999
Iacoboni et al. 1999 Buccino et al.
2001. General Purpose Perani et al. 1995
Martin et al. 1996 Grafton et al. 1996 Chao and
Martin 2000. Action-Location Bremmer, et al.,
2001.
23(No Transcript)
24FARS (Fagg-Arbib-Rizzolatti-Sakata) Model
AIP extracts the set of affordances for an
attended object.These affordances highlight the
features of the object relevant to physical
interaction with it.
Itti CS564 - Brain Theory and Artificial
Intelligence. FARS Model
25Hypothetical coordinated control program for
reaching and grasping
Perceptual Schemas
Motor Schemas
Dashed lines activation signals solid lines
transfer of data. (Adapted from Arbib 2004)
26- MULTI-MODAL INTEGRATION
- The premotor and parietal areas, rather than
having - separate and independent functions, are neurally
integrated - not only to control action, but also to serve the
function of - constructing an integrated representation of
- Actions, together with
- objects acted on, and
- locations toward which actions are directed.
- In these circuits sensory inputs are transformed
in order to - accomplish not only motor but also cognitive
tasks, such as - space perception and action understanding.
27Modeling Motor Schemas
- Relevant requirements (Stromberg, Latash, Kandel,
Arbib, Jeannerod, Rizzolatti) - Should model coordinated, distributed,
parameterized control programs required for motor
action and perception. - Should be an active structure.
- Should be able to model concurrent actions and
interrupts. - Should model hierarchical control (higher level
motor centers to muscle extensor/flexors. - Computational model called x-schemas
(http//www.icsi.berkeley.edu/NTL)
28An Active Model of Events
- At the Computational level, actions and events
are coded in active representations called
x-schemas which are extensions to Stochastic
Petri nets. - x-schemas are fine-grained action and event
representations that can be used for monitoring
and control as well as for inference.
29Model Review Stochastic Petri Nets
Basic Mechanism
1
1
Firing function -- conjunctive -- logistic
-- exponential family
30Model Review
Firing Semantics
31Model Review
Result of Firing
32Active representations
- Many inferences about actions derive from what we
know about executing them - Representation based on stochastic Petri nets
captures dynamic, parameterized nature of actions - Generative model action, recognition, planning ,
language
Walking bound to a specific walker with a
direction or goal consumes resources (e.g.,
energy) may have termination condition(e.g.,
walker at goal) ongoing, iterative action
33Lecture Overview
- Moving beyond Spatial Prepositions to Verbs
- Motor Control Schemas Recap
- A Computational Model of Motor Control Schemas
- Basic Primitives
- Demo of the X-schema model
- Applications of Model
- Actions and Inference
34(No Transcript)
35(No Transcript)
36(No Transcript)
37(No Transcript)
38(No Transcript)
39(No Transcript)
40(No Transcript)
41(No Transcript)
42(No Transcript)
43(No Transcript)
44(No Transcript)
45(No Transcript)
46(No Transcript)
47(No Transcript)
48(No Transcript)
49(No Transcript)
50(No Transcript)
51(No Transcript)
52(No Transcript)
53(No Transcript)
54Preshaping While Reaching to Grasp
55(No Transcript)
56(No Transcript)
57(No Transcript)
58(No Transcript)
59(No Transcript)
60(No Transcript)
61(No Transcript)
62(No Transcript)
63(No Transcript)
64(No Transcript)
65(No Transcript)
66(No Transcript)
67(No Transcript)
68(No Transcript)
69(No Transcript)
70(No Transcript)
71The ICSI/Berkeley Neural Theory of Language
Project
ECG
72Representing concepts using triangle nodes
triangle nodes when two of the neurons fire, the
third also fires
73Feature Structures in Four Domains
Barrett Ham Container Push
deptCS Color pink Inside region Schema slide
sid001 Taste salty Outside region Posture palm
empGSI Bdy. curve Dir. away
Chang Pea Purchase Stroll
deptLing Color green Buyer person Schema walk
sid002 Taste sweet Seller person Speed slow
empGra Cost money Dir. ANY
Goods thing
74Simulation hypothesis
- We understand utterances by mentally simulating
their content. - Simulation exploits some of the same neural
structures activated during performance,
perception, imagining, memory - Linguistic structure parameterizes the
simulation. - Language gives us enough information to simulate
75Simulation Semantics
- BASIC ASSUMPTION SAME REPRESENTATION FOR
PLANNING AND SIMULATIVE INFERENCE - Evidence for common mechanisms for recognition
and action (mirror neurons) in the F5 area
(Rizzolatti et al (1996), Gallese 96, Buccino
2002, Tettamanti 2004) and from motor imagery
(Jeannerod 1996) - IMPLEMENTATION
- x-schemas affect each other by enabling,
disabling or modifying execution trajectories.
Whenever the CONTROLLER schema makes a transition
it may set, get, or modify state leading to
triggering or modification of other x-schemas.
State is completely distributed (a graph marking)
over the network. - RESULT INTERPRETATION IS IMAGINATIVE SIMULATION!
76Simulation-based language understanding
77Simulation specification
- A simulation specification consists of
- schemas evoked by constructions
- bindings between schemas
78Language Development in Children
- 0-3 mo prefers sounds in native language
- 3-6 mo imitation of vowel sounds only
- 6-8 mo babbling in consonant-vowel segments
- 8-10 mo word comprehension, starts to lose
sensitivity to consonants outside native language - 12-13 mo word production (naming)
- 16-20 mo word combinations, relational words
(verbs, adj.) - 24-36 mo grammaticization, inflectional
morphology - 3 years adulthood vocab. growth,
sentence-level grammar for discourse purposes
79food toys misc. people
sound emotion action prep.
demon. social
Words learned by most 2-year olds in a play
school (Bloom 1993)
80Regier Model Limitations
- Scale
- Uniqueness/Plausibility
- Grammar
- Abstract Concepts
- Inference
- Representation
- Biological Realism
81Learning Verb MeaningsDavid Bailey
- A model of children learning their first verbs.
- Assumes parent labels childs actions.
- Child knows parameters of action, associates with
word - Program learns well enough to
- 1) Label novel actions correctly
- 2) Obey commands using new words (simulation)
- System works across languages
- Mechanisms are neurally plausible.
82(No Transcript)
83Reasoning about Actions in Artificial
Intelligence (AI)
- The earliest work on actions in AI took a
deductive approach - designers hoped to represent all the system's
world knowledge' explicitly as axioms, and use
ordinary logic - the predicate calculus - to
deduce the effects of actions - Envisaging a certain situation S was modeled by
having the system entertain a set of axioms
describing the situation - To this set of axioms the system would apply an
action - by postulating the occurrence of some
action A in situation S - and then deduce the
effect of A in S, producing a description of the
outcome situation S'
84Grasping the action
- A set of pre-conditions in S
- free_top(y), free_hand(x), accessible(y)
- The grasp action (effect axiom)
- Result(Grasp(x,y, S), hold(x,y,S))
- A set of effects describing the new situation S
- Hold(x,y), not(free-hand(x))
85Actions
- An action is described as an axiom linking
preconditions (literals and terms true in the
before situation) to effects (literals and terms
true in the after situation). - The action specification is called an effect axiom
86Assumptions
- Necessary and sufficient conditions
- Object categories
- Event categories
- Monotonicity
- Axioms, once asserted, cannot be retracted
- Complex for actions since actions are about
change - Closed World Assumption
87Problems with action concepts
- Frame problem
- Qualification problem
- Ramification problem
88The Frame Problem
- Which things dont change in an action
- S1 blue(x), on_table(x), free_hand(y)
- Action grasp(y,x)
- S2 in_hand(x,y), hold(x,y), ?
89Frame axioms are needed in logic
- Consider some typical frame axioms associated
with the action-type - move x onto y.
- If z ! x and I move x onto y, then if z was on w
before, then z is on w after. - If x is blue before, and I move x onto y, then x
is blue after.
90Active Representations dont need frame axioms
- X-schemas directly model change, so no need for
frame axioms. Also, they deal with concurrency,
so no need to treat one action at a time. - Based on x-schema type models there are a new set
of logics called resource logics which attempt to
model the frame problem directly.
91Logical approaches to the Frame Problem
- STRIPS assumptions
- Preconditions and effects
- Add and Delete Lists for actions
- Only one action at a time
- Non Monotonic Logics
- Circumscription (explicitly specify abnormal
conditions)
92Qualification problem
- How do I specify all the pre-conditions for an
action? - Problem arises out of the necessary and
sufficient conditions for the pre-conditions
93Approaches to the Qualification problem
- Traditional Models
- STRIPS assumption
- Modern AI Approach
- Probabilistic Models of Actions
94Ramification Problem
- How do I specify all the effects
- Direct (if I move, I change my location) and
- Indirect (things that were accessible before I
moved may not be anymore) - Central issue is to propagate changes of an
action to all the connected knowledge that might
be impacted. - How might the brain do this?
- Spreading Activation
95Solutions to the Ramification Problem
- Traditional Solution
- One action at a time
- Closed World assumption
- Modern AI Solution
- Bayes Nets and Probabilistic Models
96General Modern Solution
- Use Probabilistic Models to model the indirect
effects of actions - Graphical Models
- Stochastic Causal Models
97But
- Actions and events (and concepts in general)
- Are context sensitive
- Admit detailed structure
- Events can have starts, middles, ends..
- Have prototype structure
- Have basic level categorization structure
- Can be executed and reasoned about in parallel
- Concurrency and synchronization
98Somatotopy of Action Observation
Foot Action
Hand Action
Mouth Action
Buccino et al. Eur J Neurosci 2001
99Pattern Generator Networks
- a), Four-cell network for bipedal locomotor CPG
b), eight-cell network for quadrupeds c),
4n-cell network for 2n-legged animals. Double
lines indicate contralateral coupling single
lines indicate ipsilateral coupling. Direction of
ipsilateral coupling is indicated by arrows
contralateral coupling is bidirectional.