Artificial Life for the evolution towards Artificial Intelligence - PowerPoint PPT Presentation

Loading...

PPT – Artificial Life for the evolution towards Artificial Intelligence PowerPoint presentation | free to download - id: 12a30-ZTc1N



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Artificial Life for the evolution towards Artificial Intelligence

Description:

Good for management tasks, such as timetables and resource scheduling ... neural network brains. initial neural wiring is genetic. At birth, all neural weights ... – PowerPoint PPT presentation

Number of Views:220
Avg rating:3.0/5.0
Slides: 51
Provided by: V213
Learn more at: http://www.virgil.gr
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Artificial Life for the evolution towards Artificial Intelligence


1
Artificial Life for the evolution towards
Artificial Intelligence
  • Virgil Griffith
  • SFI Visiting Researcher
  • v_at_santafe.edu
  • http//virgil.gr
  • Santa Fe Institute CSSS 2007

2
What is Artificial Life?
Life,
3
Evolution an abbrev intro
  • Evolution is an algorithm
  • Given only
  • Variable population
  • Selection
  • Reproduction with occasional errors
  • Regardless of substrate, you get evolution!

4
What can Evolution do?
  • Optimization
  • Traffic Lights
  • Air Foil Shape
  • Linux Kernel
  • Fuzzy Problems
  • Sonar response from sunken ships versus live
    submarines
  • Good for management tasks, such as timetables and
    resource scheduling
  • Even good for evolving learning algorithms and
    simulated organisms and behaviors

5
Forming body plans with evolution
  • Node specifies part type, joint, and range of
    movement
  • Edges specify the joints between parts
  • Population?
  • Graphs of nodes and edges
  • Selection?
  • Ability to perform some task (walking, jumping,
    etc.)
  • Mutation?
  • Node types change/new nodes grafted on

6
Evolved Body Structures
Movie
7
Using artificial life and evolution for the
creation ofArtificial Intelligence
8
How to model Intelligence?
  • Marionettes (ancient Greeks)
  • Hydraulics (Descartes)
  • Pulleys and gears (Industrial Revolution)
  • Telephone switchboard (1930s)
  • Boolean logic (1940s)
  • Digital computer (1960s)
  • Neural networks (1980s - ?)

9
Nervous Systems
  • Evolution found and stuck with nervous systems
    across all levels of complexity
  • Provide all behaviorsincluding anything that
    might be considered intelligencein all organisms
    more complex than plants
  • Some behaviors are innate, so the wiring diagram
    (the connections) must matter
  • But some behaviors are learned, so
    learningphenotypic plasticitymust also matter

10
Plasticity in Neural Function
Function maps
The redirect
Mriganka Sur, et al Science 1988, Nature 2001
11
Plasticity in Wiring
Patterns of long-range connections in V1, normal
A1, and rewired A1
Mriganka Sur, et al. Nature 2001
12
Hebbian Learning Structure from Randomness
John Pearson, Gerald Edelman
13
Real and Artificial Brain Maps
Distribution of orientation-selective cells in
visual cortex
14
Neuroscience Recap
  • Intelligence is based in brains
  • Useful brain functions are created by a
  • suitable initial neural wiring
  • general purpose learning mechanism
  • Artificial neural networks capture key features
    of biological neural networks
  • Thus, we could make useful artificial neural
    systems with
  • An evolving population of wiring diagrams
  • Hebbian learning

15
(No Transcript)
16
What Polyworld is
  • An electronic primordial soup experiment
  • Making artificial intelligence the way Nature
    made natural intelligence
  • The evolution of nervous systems in an ecology
  • Working our way up the intelligence spectrum
  • Research tool for evolutionary biology,
    behavioral ecology, cognitive science

17
What Polyworld is not
  • Fully open ended
  • Accurate model of microbiology
  • Accurate model of any particular ecology
  • though could be done
  • Accurate model of any animals brain
  • though could be done

18
Polyworld Overview
  • Organisms have
  • evolving genes, and mate sexually
  • a body and metabolism
  • neural network brains
  • initial neural wiring is genetic
  • At birth, all neural weights are random
  • Hebbian learning refines synapse weights
    throughout lifetime
  • 1-dimensional vision (like Flatland)
  • No fitness function
  • Fitness is determined by natural selection alone
  • Critter Colors
  • Red current aggression
  • Blue current horniness

19
Movie - Sample
20
Body Genes
  • Size
  • Strength
  • Max speed
  • Max lifespan
  • Fraction of energy given to offspring
  • Greenness
  • Point-mutation rate
  • Number of crossover points

21
Brain Genes (Brenes)
  • Vision
  • of neurons for seeing red
  • of neurons for seeing green
  • of neurons for seeing blue
  • of internal neural groups
  • For each neural group
  • of excitatory neurons
  • of inhibitory neurons
  • Initial bias of neurons
  • Bias learning rate
  • For each pair of neural groups
  • Connection density for excitatory neurons
  • Connection density for inhibitory neurons
  • Learning rate for excitatory neurons
  • Learning rate for inhibitory neurons

22
Polyworldian brain map
23
Polyworld Brain Map (actual)
24
All about Energy (Health)
  • Get Energy by
  • eating food pellets
  • eating other Polyworldians
  • Lose Energy by
  • mating, moving, existing
  • having large size or strength
  • but get benefits in max-energy and fighting
  • brain activity
  • for computational reasons and parsimonious brain
    size

25
Behavior sample Eating
26
Behavior sample Killing Eating
27
Behavior sample Mating
28
Behavior sample Lighting
29
New Species Joggers
30
New Species Indolent Cannibals
31
Emergent Behavior Visual Response
32
Emergent Behavior Fleeing Attack
33
Foraging, Grazing, Swarming
34
Observations from Polyworld
  • Evolution generates a wide range brain wirings
  • Selection for use of vision
  • Evolution of emergent behaviors

35
Predator-Prey Cycles
36
Ideal Free Distribution in agents with evolved
neural architectures
Early
Middle
Late
37
(No Transcript)
38
But is it Alive? Ask Farmer Belin
  • Life is a pattern in space-time, rather than a
    specific material object
  • Self-reproduction
  • Information storage of a self-representation
  • A metabolism
  • Functional interactions with the environment
  • The ability to evolve

Farmer, Belin (1992)
39
But is it Intelligent?
  • No obvious way to measure intelligence
  • (aka We dont know)
  • even biologists have a hard time on this
  • But were in a simulation, that means we can use
    techniques not available to biology!
  • Information theory
  • Complexity theory

40
Neural Group Mutual Information
41
Neural Functional Complexity
42
Is there an evolutionary arrow of complexity?
  • Yes Darwin, Lamarck, Huxley, Valentine (?)
  • No Lewontin, Levins, Gould(?)

43
Evolution drives mean complexity?
44
Evolution drives max complexity?
45
Genetic complexity over time
46
Neural Complexity Room to grow
47
Future Directions
  • More
  • measures of complexity
  • complex environment
  • food types
  • agent senses (touch, smell)
  • Behavioral Ecology
  • Optimal foraging (profit vs. predation risk)
  • Evolutionary Biology
  • Speciation (population isolation)
  • Altruism (genetic similarity)
  • Classical conditioning, animal intelligence
    experiments

48
Source Code
  • Source code is available!
  • Runs on Mac/Linux (via Qt)
  • http//www.sf.net/projects/polyworld/

49
But is this a good idea?
50
Thanks to
  • Larry Yaeger
  • Chris Adami
About PowerShow.com