The Role of Artificial Life, Cellular Automata and Emergence in the study of Artificial Intelligence

rucksackbulgeΤεχνίτη Νοημοσύνη και Ρομποτική

1 Δεκ 2013 (πριν από 3 χρόνια και 17 μέρες)

66 εμφανίσεις

The Role of Artificial Life, Cellular
Automata and Emergence in the
study of Artificial Intelligence


Ognen Spiroski

CITY Liberal Studies

2005

Presentation Outline


Artificial Intelligence and Artificial Life


Complex Systems and Artificial Life


Emergence


Self
-
organization and the
edge of chaos


The Digital Worlds of Artificial Life


Cellular Automata


Conway’s Game of Life

Artificial Intelligence and

Artificial Life


Definition of AI


AI is the study of the mechanisms underlying
intelligent behaviour through the construction
and evaluation of artifacts that attempt to
enact those mechanisms


Classic AI


Logic based, symbol manipulating


Top
-
down models
simulate

intelligent
behaviour

Artificial Intelligence and

Artificial Life (cont’d)


Behaviour
-
oriented AI


Inspired by biology


“defines intelligence in terms of observed
behaviour and self
-
preservation. It is based on the
idea that the essence of biological systems is their
capacity to continuously preserve and adapt
themselves”



Bottom
-
up computational models result in
emergent behaviour

Artificial Intelligence and

Artificial Life (cont’d)


Behaviour
-
oriented AI paradigms


Connectionist


Evolutionary


Agent
-
based


Emergent


Don’t rely on a central scheme which explicitly
describes the intelligent behaviour


Through the interactions of many simple
structures, complex behaviour that is not
directly programmed is exhibited

Defining Artificial Life


Definition


the analysis and study of life and life
-
like
processes in man
-
made systems through the
use of simulation and synthesis


Why?


Broaden understanding of what life is by
building it artificially


Explore
synthetic evolution


Life
-
as
-
it
-
could
-
be vs Life
-
as
-
we
-
know
-
it

Defining Life


The problem of defining what life “is”


Life is built by simple, non
-
living components


Yet it appears to be more than the mere sum of
their interaction


Traditional definitions


Test for certain properties:


Metabolism, adaptability, self
-
maintenance,
autonomy, growth, replicability, evolution, etc.


Incomplete

Defining Life


Complex Systems


Complex Systems


Life is found in complex dynamic systems


Life requires a certain level of complexity in a
dynamic system


Defining the
threshold of complexity

which
separates living from non
-
living systems


Life
-

an
emergent phenomenon

in a
complex system

Emergence


Defining emergence


“The theory of emergence involves three propositions:


(1) that there are levels of existence . . .


(2) that there are marks which distinguish these levels from
one another . . .


(3) that it is impossible to deduce marks of a higher level
from those of a lower level . . . ”



To define life as an emergent phenomenon implies
the acknowledgement that different properties of
systems require different, qualitatively unrelated,
epistemological categories and models, which cannot
be reduced to the properties of the component parts
of the system.




Artificial Life and Emergence


Search for the

origin of life


The threshold of complexity needed for the
emergence of life



Understand life through
computational
emergence


Self
-
organization


A hallmark of emergence


Definition


the spontaneous formation of well organized
structures, patterns, or behaviors, from random
initial conditions


Found in complex dynamical systems


these systems tend to reach a particular state, or a
set of cycling states, or a small volume of their
state space, with no external interference. All the
mechanisms dictating its behavior are internal to
the system:
self
-
organization as opposed to
externally imposed organization

The Edge of Chaos


Ordered systems


Not enough complexity
for life to emerge


Chaotic systems


Too rapid changing to
self
-
organize sufficient
complexity and sustain
life


Complex systems


Life is found at
the
edge of chaos
(Langton)

Phases found in dynamical systems

The Digital Worlds of Artificial Life


Christopher G. Langton:


"The principle assumption made in Artificial Life is
that the 'logical form' of an organism can be
separated from its material basis of construction,
and that 'aliveness' will be found to be a property
of the former, not of the latter.“



Life in a logical informational universe

The Digital Worlds of Artificial Life


Simulations in the digital medium


Ease of research


Well known formal structure


Data gathering


Completely repeatable experiments


Fast


Is it “real life”?



Cellular Automata


Definition


“A cellular automaton is a discrete dynamical system.
Space, time, and the states of the system are
discrete. Each point in a regular spatial lattice, called
a cell, can have any one of a finite number of states.
The states of the cells in the lattice are updated
according to a local rule. That is, the state of a cell at
a given time depends only on its own state one time
step previously, and the states of its nearby neighbors
at the previous time step. All cells on the lattice are
updated synchronously. Thus the state of the entire
lattice advances in discrete time steps. “



An example of complex systems

Cellular Automata History


History


von Neumann and self
-
reproducing automata


Conway’s “Game of Life”


Wolfram


the Universe as a CA


The Game of Life


Invented by
mathematician John
Conway


The best known
example of a CA


Very simple, yet


An excellent example
of emergence and
self
-
organization

Game of Life
-

Definition


A two
-
state two
-
dimensional CA with three
very simple rules of action:

1. One inactive cell surrounded by three active cells
becomes active ("it's born")

2. One active cell surrounded by 2 or 3 active cells
remains active

3. In any other case, the cell "dies" or remains
inactive.

Game of Life
-

Examples


Still life objects (block, beehive, boat, ship, loaf)


They simply remain the same in the next generation


Oscillators


They change throughout generations, but essentially cycle
through the same pattern


Gliders


They move diagonally across the grid


The Queen Bee Shuttle


Spaceships


They move left, right, up or down instead of on diagonals like
gliders



Game of Life
-

Research


A completely known universe


Computation is possible


A Turing machine has been implemented


Formal proof that self
-
reproducing
mechanisms are possible



Summary


Artificial Life:


Biology inspired


Multidisciplinary approach


Computational evolution


Complex Systems


Emergence and self
-
organization


Life at the
edge of chaos


Cellular Automata


Simple, yet effective models for studies in Artificial
Life