Artificial Intelligence and Software that Learns and Evolves - PowerPoint PPT Presentation

Loading...

PPT – Artificial Intelligence and Software that Learns and Evolves PowerPoint presentation | free to download - id: 5fe3c3-NDlhY



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Artificial Intelligence and Software that Learns and Evolves

Description:

Title: Applied Interactive Story Last modified by: J Michael Moshell Created Date: 8/6/2011 7:45:48 PM Document presentation format: On-screen Show (4:3) – PowerPoint PPT presentation

Number of Views:123
Avg rating:3.0/5.0
Slides: 108
Provided by: csUcfEdu78
Learn more at: http://www.cs.ucf.edu
Category:

less

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

Title: Artificial Intelligence and Software that Learns and Evolves


1
Artificial Intelligence and Software that Learns
and Evolves
  • DIG 3563 Fall 13
  • Dr. J. Michael Moshell
  • University of Central Florida
  • Adapted from A Special Presentation
  • for Ajou University
  • Autumn 2013

hplusmagazine.com
2
The Plan of the Lecture
  • 0 What is a problem? What is intelligence?
  • 1. The classical approach logic and deduction
  • 2. The knowledge-based approach large databases
  • 3. Cognitive science models of human reasoning
  • 4. Evolutionary Computing

3
0 What is a Problem?
  • "Something that is difficult to deal with."
    (Dictionary definition)

4
0 What is a Problem?
  • "Something that is difficult to deal with."
    (Dictionary definition)
  • For a small child, this is a problem
  • Anna had 2.00. She spent 0.75 for candy.
  • How much money does Anna have now?

www.towngreendistrict.com
5
0 What is a Problem?
  • "Something that is difficult to deal with."
    (Dictionary definition)
  • For a small child, this is a problem
  • Anna had 2.00. She spent 0.75 for candy.
  • How much money does Anna have now?
  • For the President of the United States, this is a
    problem
  • Can we change the laws so that everyone has a
    job,
  • and the economy grows in a safe, steady fashion?

www.nps.gov
6
Classifying Problems
  • Problems
  • Well-formulated problems other problems
  • clear goals mixed goals
  • limited action space infinite action space
  • clear rules rules are changing

7
Classifying Problems
  • Problems
  • Well-formulated problems other problems
  • clear goals mixed goals
  • limited action space infinite action space
  • clear rules rules are changing
  • Easy Tractible Intractible
  • problems problems problems

kardwell.com
en.wikipedia.org
artsbeat.blog.nytimes.com
8
Tractible definition
  • Easily handled or worked.
  • examples
  • Wood is a tractible material for making
    furniture.
  • OPPOSITE intractible
  • Titanium is an intractible material for making
    furniture.

bizchair.com
worldchair.com
9
The Traveling Salesman Problem
A man must visit 50 cities. He must visit each
city ONE TIME. Find the shortest path for his
travel.
10
The Traveling Salesman Problem
A man must visit 50 cities. He must visit each
city ONE TIME. Find the shortest path for his
travel.
A man must visit n cities. He must visit each
city ONE TIME. Find the shortest path for his
travel. How long to compute?
11
The Traveling Salesman Problem
A man must visit 50 cities. He must visit each
city ONE TIME. Find the shortest path for his
travel.
A man must visit n cities. He must visit each
city ONE TIME. Find the shortest path for his
travel. How long to compute? time k c n
(for some constants k and c). As n gets large,
time gets VERY BIG VERY FAST
12
The Traveling Salesman Problem
for k1 microsecond and c2, 50 cities
takes 313,000 hours or 35 years!
13
Classifying Problems
  • Problems
  • Well-formulated problems other problems
  • clear goals mixed goals
  • limited action space infinite action space
  • clear rules rules are changing
  • Easy Tractible Intractible In 1975
  • problems problems problems

kardwell.com
en.wikipedia.org
artsbeat.blog.nytimes.com
14
IBM's Deep Blue Chess Playing Computer
In 1989, IBM's computer and programming team
defeated Garry Kasparov, world chess
champion. It did not defeat the exponential time
cost of chess. It simply made k and c small
enough, and explored more futures than the human
could.
ibm.com
en.wikipidia.org
15
Classifying Problems
  • Problems
  • Well-formulated problems other problems
  • clear goals mixed goals
  • limited action space infinite action space
  • clear rules rules are changing
  • Easy Tractible Intractible In 1990
  • problems problems problems

kardwell.com
en.wikipedia.org
artsbeat.blog.nytimes.com
16
Decision Trees and Exponential Time-Cost
trim-a-tree.co.uk
Many problems are analyzed by building a decision
tree and seeking a path to a winning node. Here,
n9 (nine options)
en.wikipidia.org
17
Decision Trees and Exponential Time-Cost
trim-a-tree.co.uk
If each decision leads to a growing tree of other
decisions, the time required to explore all the
branches time k c n and that is too
long for anything but very small
n.
en.wikipidia.org
18
Heuristic A plan to choose options that are
'most likely to succeed'
trim-a-tree.co.uk
Eliminate those branches that your heuristic
function tells you are not likely to succeed.
Then expand the promising ones.
en.wikipidia.org
19
Heuristic A plan to choose options that are
'most likely to succeed'
trim-a-tree.co.uk
A simple heuristic from chess Do not exchange
pieces if you lose more pawn-units than your
opponent loses.
Pawn1 unit Knight, Bishop3 pawns Rook5
pawns Queen9 pawns
20
Heuristic A plan to choose options that are
'most likely to succeed'
trim-a-tree.co.uk
A simple heuristic from chess Do not exchange
pieces if you lose more pawn-units than your
opponent loses. Example Do not exchange your
queen for two knights.
Pawn1 unit Knight, Bishop3 pawns Rook5
pawns Queen9 pawns
21
Intelligence Problem Solving Ability?
zmescience.com
Most people agree that an intelligent agent
must be able to solve some problems (not all
problems.) However, Many people feel that if
you have a well-formed problem, the hard work
has already been done. The BIG challenge is
transforming a real-world problem into a
well-formed symbolic problem.
22
Natural Language a great place to find
ill-formed problems
zmescience.com
Imagine a computer program that could answer
questions "Can a cat drive a car?" Computer
and Program
worldoffemale.com
23
Natural Language a great place to find
ill-formed problems
zmescience.com
Imagine a computer program that could answer
questions "Can a cat drive a car?" Computer
and Program "No. A cat has no hands and
cannot drive a car."
24
The Turing Test for Intelligence
Alan Turing was a British mathematician
who played a key role in World War II
code-breaking and helped to develop the digital
computer. He thought about intelligence and
proposed a test.
thocp.net
25
The Turing Test for Intelligence
Is "mystery system" intelligent? Ask questions
via a Teletype machine. Mystery System
thocp.net
Is "mystery system" a human or a machine? If you
cannot accurately decide (and it's a machine)
then the machine is intelligent. Mystery
System
26
The Turing Test for Intelligence
Has any system passed the Turing Test yet? Ask
Siri ... Most people quickly conclude that
Siri does not yet pass the Turing Test. But it's
getting better all the time...
scoopertino.com
www.apple.com
27
1. The Classical (Logical) Approach to
Artificial Intelligence
Basic concepts 1. LOGIC is powerful enough to
solve AI problems. 2. KNOWLEDGE must be
represented in a formal system. 3. INFERENCE is
the key mechanism to answer questions. All
humans will die. John is a human ?therefore,
John will die.
hci.stanford.edu/winograd
28
1. The Classical (Logical) Approach to
Artificial Intelligence
Knowledge representation as a "semantic net" of
related concepts
hci.stanford.edu/winograd
en.wikipedia.org
29
1. The Classical (Logical) Approach to
Artificial Intelligence
Example Terry Winograd's SHRDLU System A "Toy
world" of colored blocks (simulated by
computer) Questions and commands (in
English) 1) Translate into formal
propositions 2) Try to prove or disprove
them from the known facts. 3) Change system
state if possible.
hci.stanford.edu/winograd
University of Utah
30
1. The Classical (Logical) Approach to
Artificial Intelligence
Example Terry Winograd's SHRDLU System Person
Pick up a big red block Computer OK Person
Grasp the pyramid
hci.stanford.edu/winograd
University of Utah
31
1. The Classical (Logical) Approach to
Artificial Intelligence
Example Terry Winograd's SHRDLU System Person
Pick up a big red block Computer OK Person
Grasp the pyramid Computer I don't understand
which pyramid you mean. (because there are two
of them.)
hci.stanford.edu/winograd
University of Utah
32
1. The Classical (Logical) Approach to
Artificial Intelligence
Example Terry Winograd's SHRDLU System Watch the
SHRDLU movie (3 minutes 20 seconds of it)
University of Utah
33
1. The Classical (Logical) Approach to
Artificial Intelligence
Excitement! SHRDLU worked for Blocks
World. followed by Disappointment Most
domains are MUCH harder.
hci.stanford.edu/winograd
34
2. The Knowledge-Based Approach
Doug Lenat's talk at Google Brittle
Software (Lenat video first 14 minutes)
35
2. The Knowledge-Based Approach

Key concept Today we have brittle (easily
broken) software Danger Power is in the hands
of "smart idiots". Examples of Cyc's
successes Request Find a picture of someone
smiling ? Cyc found picture of a man helping
his daughter take her first step Request
Find something that could harm an airplane ? Cyc
located a video about an SA-7 missile
36
2. The Knowledge-Based Approach
LARGE databases of facts. If SHRDLU's world was
too small, let's build a big world of
knowledge. Cyc Project started in 1984 by
Douglas Lenat Estimated effort (1986) 250,000
rules and 350 man-years of effott. Up until
now gt1 million rules, and no end in sight.
37
2. The Knowledge-Based Approach
LARGE databases of facts. If SHRDLU's world was
too small, let's build a big world of
knowledge. Cyc Project started in 1984 by
Douglas Lenat cYcorp distributes the OpenCyc
4.0 database (for free), with 239,000
terms 2,093,000 "triples" (rules) that
attempt to represent human common sense.
38
2. The Knowledge-Based Approach
cYcorp also has a private database with
many more assertions and rules, in the CycL
language. Example (isa BillClinton
UnitedStatesPresident)
cycorp.org
39
Cyc An example of the complexity
cycorp.org
University of Utah
40
Cyc Method for Growing the Database
Attempt to automatically read encyclopedia
articles. (enCYClopedia!) Analyze successes
failures Apply human "knowledge engineering" to
improve rules
41
Cyc example Terrorism Database
Analyze literature on terrorism Predict
future events. Success ? predicted anthrax
mailings, 6 months before 9/11 Miss ? Predicted
1000 dolphins from Al-Qaeda to attack Hoover
Dam
www.usbr.gov
42
Cyc Status and Hope for the Future
Cyc will eventually become smart enough to teach
itself. The results thus far Government
sponsors basic research and terrorism database
Some commercial applications are being tried.
43
Cyc Status and Hope for the Future
Cyc will eventually become smart enough to teach
itself. The results thus far Government
sponsors basic research and terrorism database
Some commercial applications are being tried.
Many people in the Artificial Intelligence
community doubt that Cyc will play a key role
in successful AI Why? It's too logical. Humans
are inconsistent, emotional, intuitive they
act on their FEELINGS --
44
3. Cognitive Science How Humans Think
wikimedia commons
45
Philosophy
Example Mind-Body Problem Is the mind part of
the body? Or separate? Metaphors "The brain
is a telephone switchboard" "The brain is a
computer" ? Mind is software (can be
changed) Brain is hardware (can be
broken) ? New ideas on good and evil
46
Philosophy
Example Deductive Logic If A, and A?B, then
B A A Hyundai is a car B Cars are made by
humans so Hyundais are made by humans
47
Philosophy
Inductive logic If the events in class C are
probable, and A is in class C, then A is
probable. 90 of humans are right-handed. Jack
is a human. so Jack is probably
right-handed.
48
Philosophy and Intelligence
If a thing is intelligent, we expect it to use
deductive logic and inductive logic.
49
Psychology
Definition Study of mental functions and
behaviors Example Memory
wikipedia.org/mimory
50
Psychology
Definition Study of mental functions and
behaviors Some types of long-term
memory Procedural (how to do something)
everyculture.com
51
Psychology
Definition Study of mental functions and
behaviors Some types of long-term
memory Procedural (how to do something) Topogra
phic (where am I, where am I going)
mycharlois.com
52
Psychology
Definition Study of mental functions and
behaviors Some types of long-term
memory Procedural (how to do something) Topogra
phic (where am I, where am I going) Episodic
(what happened)
fleetowners.com
53
Psychology
en.wikipedia.org
Definition Study of mental functions and
behaviors Some types of long-term
memory Procedural (how to do something) Topogra
phic (where am I, where am I going) Episodic
(what happened) Semantic (facts, definitions,
abstract knowledge)
54
Psychology
Definition Study of mental functions and
behaviors Some types of long-term
memory Procedural (how to do something) Topogra
phic (where am I, where am I going) Episodic
(what happened) Semantic (facts, definitions,
abstract knowledge) Visual (I've seen this
before)
bic.org
55
Psychology
Definition Study of mental functions and
behaviors Some types of long-term
memory Procedural (how to do something) Topogra
phic (where am I, where am I going) Episodic
(what happened) Semantic (facts, definitions,
abstract knowledge) Visual (I've seen this
before) Emotional (things I loved or hated)
gofamilyperks.com
56
Psychology
If a thing is intelligent, we expect it to
need (and have) most of the types of
memory that humans have. Why? (back to
Philosophy!)
57
Psychology
If a thing is intelligent, we expect it to
need (and have) most of the types of
memory that humans have. Why? Inductive
logic. "Most of the intelligent creatures we
have seen, had these kinds of memory".
58
Linguistics Scientific Study of Language
Key insight Analogies carry meaning. Definition
An analogy is a comparison of two systems. If
you understand system A, it can help you to
understand system B. Analogy Simile Metaphor
59
Linguistics Scientific Study of Language
Key insight Analogies carry meaning. Definition
An analogy is a comparison of two systems. If
you understand system A, it can help you to
understand system B. Analogy "The motor of a
car is like a horse pulling a
wagon." Simile Metaphor
60
Linguistics Scientific Study of Language
Key insight Analogies carry meaning. Definition
An analogy is a comparison of two systems. If
you understand system A, it can help you to
understand system B. Analogy "His mother was
a tiger!" Simile Metaphor
61
Linguistics Scientific Study of Language
Key insight Analogies carry meaning. Science is
based on analogies. Example Bohr's "Solar
system" model of the atom.
ou.org
wikipediaorg
62
Linguistics
If a thing is intelligent, we expect that it
will understand and use a natural language
(like English or Korean). and we expect that
it will make and use analogies to extend and
communicate its knowledge.
63
AI and Cognitive Science Marvin Minsky makes an
analogy
  • Minsky's theory of mind
  • The mind is like a complex software system.
  • The pieces of this software system will interact
  • in ways that are different from traditional
    software.
  • They will interact like a "society".

64
AI and Cognitive Science Marvin Minsky makes an
analogy
  • Minsky's theory of mind
  • A mind is a large collection of small agents
  • They compete for control of the
  • front office (consciousness)
  • The all or none theory. You cant half walk
    and half sit.
  • Many of these agents are working at any time

65
Interior Grounding, Reflection and
Self-Consciousness A woman named Joan is
crossing the street. A car sounds its horn.
66
Interior Grounding, reflection and
Self-Consciousness A story about a woman
crossing the street.
  • Reaction Joan reacted quickly to that sound.
  • Identification She recognized it as being a
    sound.
  • Characterization She classified it as the sound
    of a car.
  • Attention She noticed certain things rather than
    others.
  • Indecision She wondered whether to cross or
    retreat.

67
Interior Grounding, reflection and
Self-Consciousness A story about a woman
crossing the street.
  • Reaction Joan reacted quickly to that sound.
  • Identification She recognized it as being a
    sound.
  • Characterization She classified it as the sound
    of a car.
  • Attention She noticed certain things rather than
    others.
  • Indecision She wondered whether to cross or
    retreat.
  • Imagining She envisioned some possible future
    conditions.
  • Selection She selected a way to choose among
    options.
  • Decision She chose one of several alternative
    actions.
  • Planning She constructed a multi-step
    action-plan.
  • Reconsideration Later she reconsidered this
    choice.

68
Marvin Minsky Interior Grounding, Reflection and
Self-Consciousness These processes can be
classified something like this
.. which is similar to Freuds model
69
Marvin Minsky Interior Grounding, reflection and
Self-Consciousness
70
Minsky doesnt like the bottom-up idea that
sensations (alone) could lead to higher
thought. He believes in a rich set of
built-in capabilities. The details of
which language, what culture, what house and
street are learned by each individual.
71
Minsky's Influence
  • "Societies of Mind" has not yet led to a working
    AI system
  • .. but Minsky's early work led to the study of
    Neural Nets
  • (our next topic)

72
5. Neural Nets, Perception and Learning
73
4. Artificial Evolution Nature "learns" by
creating new species. Can we model that
process, to solve problems?
bio100.nicerweb.net
74
Evolutionary Computing Reviewing Genetics
  • Sexual reproduction has a big payoff. What is
    it?
  • ( In other words why are males worth having?)
  • Observation bacteria and viruses without SR
  • have evolved several mechanism for swapping DNA.
  • Its almost as if the fundamental underlying
  • metaphor for life is a flea market.

www.ryctx.org
75
Evolutionary Computing Genetics Reviewed
  • KNOWN BEFORE DNA was discovered
  • The genome is a (very) long sequence of Genes
  • Each gene controls the production of one kind of
    protein
  • Proteins are catalysts for chemical reactions
  • as well as the structural steel of living
    organisms.
  • A GENE represents a finite alphabet of choices.
  • The various versions of a gene are called
    alleles.
  • If there are 10 ways to make collagen, there
    would be
  • 10 alleles for the collagen gene.

76
  • Genotype and Phenotype
  • Genotype your collection of genes
  • Phenotype your rendering your
  • actual body, as built.
  • Genes, encoded in DNA, are organized into
    chromosomes
  • Individual humans have 23 pairs of chromosomes
  • When reproducing,
  • each parent randomly
  • contributes one of the
  • two chromosomes to
  • the child.

77
Genotype and Phenotype Mom Dad
  • X X
  • X X
  • X X
  • ... 23 X X

78
Genotype and Phenotype Mom Dad
  • X X
  • X X
  • X X
  • ... 23 X X

79
Genotype and Phenotype Mom Dad
  • X X
  • X X
  • X X
  • ... 23 X X

80
Genotype and Phenotype Mom Dad
A given pair of parents can produce 223 8
million different genetic combinations.
  • X X
  • X X
  • X X
  • ... 23 X X .. its a GIRL!

81
  • Why does this system pay such big dividends?
  • The gene pool is a toolkit of variations.
  • Consider melanin. Assume variations from black
    to brown
  • in various versions of the melanin gene.
  • Your tribe moves from Africa to Europe.
  • Your random genome remix produces kids of
    various shades.
  • The ones with lighter skin get more vitamin D
    and thrive.
  • They have more kids. The light-skin gene
    increases in the
  • gene pool. Feedback loop.

82
  • Why does this system pay such big dividends?
  • The gene pool is a toolkit of variations.
  • Consider melanin. Assume variations from black
    to brown
  • in various versions of the melanin gene.
  • Your tribe moves from Africa to Europe.
  • Your random genome remix produces kids of
    various shades.
  • The ones with lighter skin get more vitamin D
    and thrive.
  • They have more kids. The light-skin gene
    increases in the
  • gene pool. Feedback loop.
  • NOTE You didnt have to INVENT the variation
    (mutation).
  • You had it stored away in your toolkit (genome).
  • Mutation (creation of new alleles or genes) is
    MUCH slower
  • than selection among existing alleles.
  • You need BOTH mechanisms.

83
  • Mutation the big Disaster/Opportunity
  • Mutations are rare and usually fatal
  • A copying error occurs in a chromosome
  • - some DNA is duplicated
  • - some DNA is deleted
  • - one codon (and its amino acid) replaces
    another
  • Some mutations are beneficial but most are fatal
    or neutral (now)
  • A slightly different kind of hemoglobin might
    not kill you
  • but might turn out to be BETTER, against some
    parasite
  • that attacks your great great great ....
    grandchildren

84
  • Diversity yields robustness
  • The environment produces an infinite suite of
    challenges.
  • A rich gene pool provides instant options to
    try.
  • A narrow gene pool is a ticket to extinction
    (florida panthers.)
  • Hybrid vigor is a concept that every farmer
    knows.
  • Cross Hereford and Angus cows calves grow
    faster.

85
  • Diversity yields robustness
  • The environment produces an infinite suite of
    challenges.
  • A rich gene pool provides instant options to
    try.
  • A narrow gene pool is a ticket to extinction
    (florida panthers.)
  • Hybrid vigor is a concept that every farmer
    knows.
  • Cross Hereford and Angus cows calves grow
    faster.
  • Its like NAFTA or the European Union.
  • Win-win really is possible! Your kids will
    survive better
  • if your partners tool-set complements rather
  • than replicates your own.

86
  • Unnatural selection
  • To build a learning system we need three
    things
  • a genotype (a coded representation)
  • a phenotype (a rendering into a real world of
    competition)
  • a fitness function (something to measure and kill
    the losers)

87
  • Unnatural selection
  • To build a learning system we need three
    things
  • a genotype (a coded representation)
  • a phenotype (a rendering into a real world of
    competition)
  • a fitness function (something to measure and kill
    the losers)
  • Is a self-replicating robot without a genome
    impossible?
  • That is not proven. But all examples thus far
    are trivial.
  • (Crystal growth)

www.dpchallenge.com
88
  • A Genotype for Mini-Robots
  • Karl Sims decided to use a graph-theory genome
  • It is applied twice once for body, once for
    nervous system
  • A random pool of 300 genomes is built
  • they are pre-selected by removing
  • creatures with more than N body parts
  • creatures whose body parts interpenetrate (share
    space)
  • Rules of the universe are established e. g.
    gravity, a floor
  • Goal (fitness function) is set e. g. radius
    crawled in 1 minute.
  • Run simulation. Keep best 1/5 of population (60
    individuals)
  • Re-mix genes to replace the 240 who died.
  • Run the simulation again.

89
  • A Genotype for Mini-Robots
  • Some of the goals
  • - radial distance traveled
  • - linear distance traveled
  • - distance swum (or flown) through fluid medium
  • - speed of approach toward a moving target point
  • - competition to capture a shared object

90
  • A Genotype for Mini-Robots
  • Some of the goals
  • - radial distance traveled
  • - linear distance traveled
  • - distance swum (or flown) through fluid medium
  • - speed of approach toward a moving target point
  • - competition to capture a shared object
  • Competitive events how do you pair them up?
  • - n x n takes n2 time, and is too slow (each sim
    is slow!)
  • - pairwise often means playing against an idiot.
  • - n vs. best-of-last-round seemed to work well.

91
  • A Genotype for Mini-Robots
  • Some of the goals
  • - radial distance traveled
  • - linear distance traveled
  • - distance swum (or flown) through fluid medium
  • - speed of approach toward a moving target point
  • - competition to capture a shared object
  • Competitive events how do you pair them up?
  • - n x n takes n2 time, and is too slow (each sim
    is slow!)
  • - pairwise often means playing against an idiot.
  • - n vs. best-of-last-round seemed to work well.
  • One-species versus two-species (breeding
    populations)

92
NOW watch the movie at http//www.youtube.com/wat
ch?vJBgG_VSP7f8
www.dpchallenge.com
93
  • A Genotype for Mini-Robots
  • So ... how was this done?
  • NODE and LINK
  • (The names are just
  • to help us think.)
  • Example 1
  • From a segment,
  • link to two other segments.
  • Repeat any number
  • of times, recursively.

Example 1
94
  • A Genotype for Mini-Robots
  • So ... how was this done?
  • NODE and LINK
  • (The names are just
  • to help us think.)
  • Example 2
  • From a body segment,
  • link to one other body seg.
  • and two leg segments.
  • From a leg segment
  • link once to another leg segment.

Example 2
95
  • A Genotype for Mini-Robots
  • So ... how was this done?
  • NODE and LINK
  • (The names are just
  • to help us think.)
  • Example 3
  • From a body,
  • link to a head four limbs.
  • From a limb, link to another limb.

Example 3
www.dpchallenge.com
96
Brains and bodies
  • Each sensor is contained in a specific body part
  • Sensors measure joint angles, forces, properties
    of the world
  • The brain is a network of neurons (but not
    like real ones)
  • Neurons functions include sum, product,
    sum-threshold,
  • greater than, .... sin, cos, log, integrate,
    differentiate,
  • ... smooth, memory, oscillate-wave,
    oscillate-sawtooth

97
Neurons in Segments
  • P0, P1 are photosensors
  • C0 and Q0 are contact sensors
  • E0 and E1 are effectors (joint angle drivers)
  • The connections are evolved, not reasoned out.
  • (There is a graph genome for the neurons, too.)

98
Neurons in Segments
  • P0, P1 are photosensors
  • C0 and Q0 are contact sensors
  • E0 and E1 are effectors (joint angle drivers)
  • The connections are evolved, not reasoned out.
  • (There is a graph genome for the neurons, too.)

99
Neurons in Segments
  • A single shared neuron
  • group is also provided.
  • (where is it? Unspecified)
  • This capability allows for
  • coordinated control.

100
Neurons in Segments
  • A single shared neuron
  • group is also provided.
  • (where is it? Unspecified)
  • This capability allows for
  • coordinated control.
  • The saw and wav oscillators
  • are key elements.

101
What Changes in each Generation?
  • NOTE The system mixes sexual reproduction with
    mutation
  • in an un-biological way mutation occurs in
    every generation.
  • MUTATION
  • Internal parameters (weights, oscillation
    frequencies) are
  • randomly altered. Small alterations more likely
    than big ones.
  • A new random node is added to graph. (May not
    connect will be
  • discarded if not.)
  • New random connections are added, existing ones
    are removed.
  • Unconnected elements are garbage-collected.
  • Outside (morphology) graphs are altered, then
    inside (neuro) ones.

102
What Changes in each Generation?
MATING the GRAPHS a. Crossover operation. A
subset of parent 2 is inserted to replace a
subset of parent 1
103
What Changes in each Generation?
MATING the GRAPHS a. Crossover operation. A
subset of parent 2 is inserted to replace a
subset of parent 1
104
What Changes in each Generation?
MATING the GRAPHS b. Grafting operation. Two
parents are joined together (each loses one node)
105
  • Results
  • Interbreeding populations often converge to
    uniformity, but
  • Successive runs often produce totally different
    results.
  • Swimming produced
  • - paddles
  • - tail wagglers
  • - specialized scullers
  • - lots of flippers
  • - water snakes

106
  • Results
  • Interbreeding populations often converge to
    uniformity, but
  • Successive runs often produce totally different
    results.
  • Walking produced
  • - corner-walkers
  • - rocking blocks
  • - inchworms
  • - legs
  • - hoppers
  • Light-following worked in
  • walking and swimming
  • environments.

107
  • What happened next?
  • not much (at least, nothing so spectacular as
    Sims creatures.)
  • Why?
  • The leap from simple goal-seeking motor activity
    (tropisms) to
  • interesting perception and cognition is
    verrrrrry looooong.
  • Folks like Brooks and Minskys successors are
    trying
  • to bridge the gap.
  • Fundamental insights are still needed.
About PowerShow.com