Transcript Bio Inspired Computing

Bio-Inspired Computing
Overview & Biased History
Based on presentation by
Netta Cohen
from University of Leeds
What is Bio-Inspired Computing
all about?
Bio-inspired computing
Biological computation
Artificial Intelligence
2
The First Computer
Charles Babbage (1791-1871):
Inventor of difference engine –
recognised as direct ancestor
of the modern computer.
First (non-biological)
digital machine.
3
How bioinspired
computing works?
• Autonomous cells
• Messages (data, sender & receiver addresses)
• Operations (contained in message)
• Cell differentiation (context-dependent functionality)
What good is this?
‘Building’ programs the way civil engineers design buildings.
programmers can create objects to mimic generic conceptual
building blocks: No need for a new language with each
application.
4
AI programming
Bioinspired programming stands in stark contrast to familiar
AI programming languages. In 1959, John McCarthy
suggested a programming language with common sense.
Common sense: the ability to deduce for one’s self a
sufficiently wide class of consequences based on available
information.
Lisp (List Processing): logical operations represented as
manipulations of lists. Even functions and procedures are
defined as lists.
McCarthy’s goal in designing Lisp was - and still is - “to make
a machine that would be as intelligent as a human.”
5
Principles of AI
The Symbolic Search Hypothesis:
“A physical symbol system exercises
its intelligence in problem solving by
search – that is, by generating and
progressively modifying symbol
structures until it produces a solution
structure.”
Good solutions benefit from appropriate representations.
Good solutions rely on appropriate heuristics (rules of thumb).
These principles date from AI’s earliest beginnings…
6
The Birth of AI
In the 1940s Alan Turing was already speculating on…
1. …the possibility of general computer intelligence –
abstract games: good initial tasks ‘requiring little
contact with the outside world’…
2. …the potential for a computer chess player –
search algorithms to used to find good moves…
3. …a way of deciding whether a computer was
intelligent – the Turing Test is a totally disembodied
interrogation (but a somewhat situated one)…
Artificial Intelligence is an attempt to simulate reasoning as:
abstract, formal, disembodied, symbol manipulation.
7
“Intelligence w/out Reason”
Rodney Brooks (“Intelligence Without Reason”): Critic of
the AI approach & strong proponent of embodiment and
situatedness in bioinspired computing (BIC).
AI, he claims, followed the abstract route due to
technological gaps in the 40s & 50s.
Today, he says, it’s time to move on.
Brooks recognised that life-like systems are often
intelligent to some degree, yet reasoning is primarily
considered to be a human attribute. Rather than modelling
complicated human behaviour, why not start simple?
8
Why Not The Whole Iguana?
• Traditional computing is task-oriented (vertical).
• To survive, animals have to be good across the board!
Walking
Sex
Memory
Chess
Iguana
Cricket
Horizontal
Vertical
Human
Ant
Rather than build parts of human intelligence, why not
build an entire much simpler intelligence?
9
AI vs BIC
Overlap between AI and BIC is
considerable, but there are also
distinctions. BIC might be the
follower of AI. However, it could also
be regarded as a rebel.
• building (esp. human-like) intelligent machines with
common sense & decision making that naively
belies deductive logic.
• using them to improve our understanding of human
intelligence.
BIC • building life-like systems (utilising cartoon models of
biological systems, tasks & concepts).
• using them to improve our understanding of biology
AI
10
SHRDLU
By 1972, Terry Winograd’s invented a
simulated robot arm surrounded by blocks
of various shapes and colours on a table.
SHRDLU could…
•
•
•
•
understand natural language instructions
ask questions to disambiguate these instructions
act & reason in a simulated “blocksworld” environment
answer questions about the world & its own reasoning
In Winograd’s words, it was “a computer program which
‘understands’ language in a limited domain.”
SHRDLU’s algorithms carried out model building,
search, planning and logical deduction.
See for example: http://hci.stanford.edu/cs147/examples/shrdlu/
11
A Conversation with SHRDLU
> Pick up a big red block.
OKAY.
> Grasp the pyramid.
I DON’T KNOW WHICH PYRAMID YOU MEAN.
> What does the box contain?
THE BLUE PYRAMID AND THE BLUE BLOCK.
> I own blocks which are not red, but I don’t own
anything which supports a pyramid.
I UNDERSTAND.
> Do I own the box?
NO.
(adapted from Dreyfus’ 1979 What Computers Can’t Do)
12
Is that really how our brain works?
John Von Neumann, father of modern high-speed
computers also thought about neuro-computation and
tried, for the first time, to construct a meaningful
comparison between brain and computer power.
Von Neumann argued that the brain must employ digital
computation. Figuring in the number of neurons,
connections, and estimates of computational speed and
statistical noise in the brain, he then concluded that the
brain could not be explained by logic alone.
In fact, he apparently postulated (and began writing) an
alternative theory but died soon after.
13
The manuscript (published post mortem) ends as follows:
“The Language of the Brain is Not the Language of Mathematics …
whatever language the central nervous system is using, it is
characterized by less logical and arithmetical depth than what we
are normally used to … Consequently, there exist here different
logical structures from the ones we are ordinarily used to...
… whatever the system is, it cannot fail to differ considerably from
what we consciously and explicitly consider as mathematics.”
(John Von Neumann, The Computer and the Brain, 1958.)
In a recent commentary, Harold Morowitz writes:
“Von Neumann challenged the validity of the underlying
conceptualizations we use to study the brain and compare it with
computers. Yet, what is surprising, given the great esteem for John
Von Neumann, is that no one has taken up on his argument and
fully developed its consequences in the mind versus artificial
intelligence arguments that had been waging the last few years.” 14
Chess vs. Football
Chess
• Discrete
• Full Information
• Single Opponents
• Turn Taking
• Limited Options per Turn
• Intellectual, disembodied
• Optimal Strategy Exists?
• Demands General Intelligence?
• Formal, Analytical, Symbolic
Football
• Continuous
• Partial Information
• Heterogeneous Teams
• Continuous Confrontation
• Unlimited Options
• Physical, embodied
• No Optimal Strategy?
• Demands Specialist Skills?
• Dynamic, Physical, Reactive
Can the problems faced by footballers be solved through
symbol processing and heuristic search?
15
Recent developments
Autonomous Mobile Robots
1990s: roboticists turn to building simple, robust, insectlike robots geared towards performing tasks that belie
their mediocre brains.
Brooks’ autonomous mobots embody the new philosophy:
– embedded, embodied, and unencumbered by intellect –
“fast, cheap, and out of control”
16
Take home message...
What is BIC and what does it want to achieve?
Bio-inspired
computing
Biological
computation
or
Artificial
Intelligence
17
Popular Reading
• “John McCarthy: The uncommon logician of common
sense”, in Shasha & Lazere (1995).
• “Alan Kay: A clear romantic vision”, ibid.
• “Computers and Brains”, in Morowitz (1997).
Additional Papers
• “Intelligence without reason” – Brooks (1991).
At home
• Reading
• Set-up BEAST. Instructions can be found on:
http://www.comp.leeds.ac.uk/ai23/BEAST/index.php
18
BIC Structure
• Key Topics include
–
–
–
–
–
–
–
Artificial neural networks
Evolutionary design and genetic algorithms
Co-evolutionary design
Multi-agent systems and swarm Intelligence
Artificial life
Robotics and control
Interfacing biology with silicon
19
Some basics
• Think, read, ask questions, tinker, and have fun!
• Warning: Some of the material covered is, or recently
was, cutting edge.
• There will be programming, some biology, some
philosophy.
• There is a lot of material to cover, but…
lecture slides will not tell the whole story.
• You should install and familiarise yourself with the
module courseware – BEAST – starting NOW.
• Show enthusiasm, play, contribute original code.
Originality and innovation will be rewarded.
20
Resources
• Course Website: http://www.comp.leeds.ac.uk/ai23
– Lecture Slides
– Reading Lists
– Assignments
– Useful Links
• Each other
– Talk about the material.
– Talk about the assignments.
– Help each other; feel free to work together, but
– Submit only you own personal original work.
• Newsgroups:
local.modules.ai23 and
...ai23.talk
• Reading available in library, or via links on course
page.
21