Prerequisites for a Theory of Intelligence

1
Prerequisites for a Theory of Intelligence

• - G. Ananthakrishnan
• - Simon Benjaminsson

2
Popper Vs Feyerabend

• Popper
• The Logic of Scientific Discovery
• Theory has temporary status
• Falsifiability of a theory
• Against psuedo-theories like Freudian psychology
  etc.

• Feyerabend
• Against Method
• No precise rules
• Anything goes
• Anarchist approach to scientific theory

3
Abstraction, Algorithms, Dynamical Systems etc.

• Abstraction is necessary
• Principles of systems can be predicted, but
  specific system needs some empirical values
• Can a theory of intelligence be algorithmic?
• Can we have an algorithm which computes and
  thereby explains all intelligence?
• Dynamic systems chaos theory
• Structured systems emerge from chaotic conditions
• Analytical component Design aspect

4
Diversity (exploitation) - Compliance

• Soft Rules
• Choice about compliance
• Syntax Vs Semantics Grammar Vs Content
• Grammatically incorrect no compliance
• Grammatically correct, but repetitive no
  diversity
• Hard Rules
• Laws of Physics
• No choice but to comply
• Only possible to exploit
• Rock only complies, does not exploit

5
Exploitation and Knowledge

• Rock flowing down river
• does not exploit, no diversity,
• only complies with fluid dynamics
• Asimo robot that can dance, walk etc.
  diversity, exploits friction and gravity
• Fish exploits fluid dynamics
• Do they know they are exploiting?
• Humans write poems, exploiting some figures of
  speech, possibly breaking some soft rules
• Do we know? Do we need to know?

6
Stability-Flexibility (accommodation -
assimilation)

• Category learning
• Representation of the world
• Do we need only one example or several examples?
• Role of the right features?
• Categorizing unknown objects
• Soft categorization
• Exploration-Exploitation

7
Frame-of-reference problem

• An intelligent agent
• Conforms to rules/laws (Hard or Soft)
• Exploits the environment
• Exhibits diverse behavior
• May or may not be aware of this behavior
• Complex behavior with simple rules
• e.g., beach ant walks around puddles, twigs etc.
  without knowing what the obstacles are
• From ant's perspective simple rules
• From observer's perspective complex behavior

8
Swiss Robots

• The Swiss Robots Demo

• Simple rules
• Unexpected behavior
• Robots do not see cubes
• Intelligent? - Depends on perspective
• Different location of sensors?

9
Interaction - Emergence

• Robot's perspective reaction to sensory
  stimulus
• Our perspective cleaning up of Styrofoam cubes
• Effect of interaction of internal mechanism with
  environment
• Behavior cannot be estimated solely by the
  internal mechanism embodiment, environment
• Emergence of complexity from simple rules and
  interaction with environment
• What if cubes were heavier, what if sensor was
  placed differently, what is the cubes were
  slightly larger or slightly smaller?

10
Robot Puppy

• Motor and spring mechanism copies the gait of a
  puppy
• Uses pressure sensors on the feet to sense the
  ground
• Hip and shoulders are moved periodically

Theo jansen's kinetic animals
Pressure Sensors
New Species, Ted Talk (2.14 mins)

• The dog sees the world from the view of its
  sensors
• Complex gait mechanism from simple principles

11

• Over to Simon

12
Articulation- Acoustics

• Motor movement
• Visual representation
• Spatial-to-Motor reference frame
• Invariant (for the same posture)
• Bias for certain arm postures
• Articulator movement
• Acoustic representation
• Invariant? e.g. American /r/
• Highly non-linear
• Frame-of-reference?

13
Role of Embodiment

• Vocal-tract to Sound (Maeda Model)
• Application of fluid dynamics and computation of
  tube resonances.
• Control of vocal-tract parameters
• Inertia of articulators
• Muscles that control articulation
• Degrees of freedom for articulation
• Planning of articulation
• Targets and paths
• Acoustic/Perceptual features

14
The Diva System
GOF Neural Network
?
Embodiment
Partial Embodiment
15
Reference Frames

• Articulatory
• Degrees of freedom
• Constriction
• Motor equivalence
• One-many mapping with Articulatory frame
• Acoustic/Perceptual
• Formant frequency differences

16
Variance in Constriction
17
Some Equations
18
Solving a specific problem Variation in /r/
19
Explained by DIVA
Resulting configuration of /r/ Bunched
Resulting configuration of /r/ Retroflexed
20
Some videos Other applications of DIVA
Random Babbling
Reduplicated Babbling
21
Some videos Other applications of DIVA
Attempt 3
Attempt 2
Attempt 1
22
Some videos Other applications of DIVA
Simulation of Stuttering (as predicted by DIVA)
23
Thank You

• Any Questions?