1.1 --- a/org/intro.org	Wed Nov 02 11:03:12 2011 -0700
     1.2 +++ b/org/intro.org	Thu Nov 03 08:28:26 2011 -0700
     1.3 @@ -2,6 +2,7 @@
     1.4  #+author: Robert McIntyre
     1.5  #+email: rlm@mit.edu
     1.6  #+description: Simulating senses for AI research using JMonkeyEngine3
     1.7 +#+keywords: Alan Turing, AI, sinulated senses, jMonkeyEngine3, virtual world
     1.8  #+SETUPFILE: ../../aurellem/org/setup.org
     1.9  #+INCLUDE: ../../aurellem/org/level-0.org
    1.10  #+babel: :mkdirp yes :noweb yes
    1.11 @@ -14,7 +15,7 @@
    1.12  already. What idea could be missing?
    1.13  
    1.14  When Turing first proposed his famous "Turing Test" in the
    1.15 -groundbreaking paper [[./sources/turing.pdf][/Computing Machines and Intelligence/]], he gave
    1.16 +groundbreaking paper [[../sources/turing.pdf][/Computing Machines and Intelligence/]], he gave
    1.17  little importance to how a computer program might interact with the
    1.18  world:
    1.19  
    1.20 @@ -42,25 +43,24 @@
    1.21  your life from birth, you would never learn anything, and could never
    1.22  become intelligent. Actual humans placed in sensory deprivation
    1.23  chambers experience hallucinations and can begin to loose their sense
    1.24 -of reality in as little as 15 minutes[sensory-deprivation]. Most of
    1.25 -the time, the programs we write are in exactly this situation. They do
    1.26 -not interface with cameras and microphones, and they do not control a
    1.27 -real or simulated body or interact with any sort of world.
    1.28 +of reality. Most of the time, the programs we write are in exactly
    1.29 +this situation. They do not interface with cameras and microphones,
    1.30 +and they do not control a real or simulated body or interact with any
    1.31 +sort of world.
    1.32  
    1.33  * Simulation vs. Reality
    1.34  I want demonstrate that multiple senses are what enable
    1.35  intelligence. There are two ways of playing around with senses and
    1.36  computer programs:
    1.37  
    1.38 +
    1.39 +** Simulation
    1.40  The first is to go entirely with simulation: virtual world, virtual
    1.41  character, virtual senses. The advantages are that when everything is
    1.42  a simulation, experiments in that simulation are absolutely
    1.43  reproducible. It's also easier to change the character and world to
    1.44  explore new situations and different sensory combinations.
    1.45  
    1.46 -
    1.47 -** Issues with Simulation
    1.48 -
    1.49  If the world is to be simulated on a computer, then not only do you
    1.50  have to worry about whether the character's senses are rich enough to
    1.51  learn from the world, but whether the world itself is rendered with
    1.52 @@ -75,7 +75,7 @@
    1.53  dust. Maybe a simulated world with today's limitations doesn't provide
    1.54  enough richness for real intelligence to evolve.
    1.55  
    1.56 -** Issues with Reality
    1.57 +** Reality
    1.58  
    1.59  The other approach for playing with senses is to hook your software up
    1.60  to real cameras, microphones, robots, etc., and let it loose in the
    1.61 @@ -107,16 +107,15 @@
    1.62  * Choose a Simulation Engine
    1.63  
    1.64  Mainly because of issues with controlling the flow of time, I chose to
    1.65 -simulate both the world and the character. I set out to make a minimal
    1.66 -world in which I could embed a character with multiple senses. My main
    1.67 -goal is to make an environment where I can perform further experiments
    1.68 -in simulated senses.
    1.69 +simulate both the world and the character. I set out to make a world
    1.70 +in which I could embed a character with multiple senses. My main goal
    1.71 +is to make an environment where I can perform further experiments in
    1.72 +simulated senses.
    1.73  
    1.74 -As Carl Sagan once said, "If you wish to make an apple pie from
    1.75 -scratch, you must first invent the universe." I examined many
    1.76 -different 3D environments to try and find something I would use as the
    1.77 -base for my simulation; eventually the choice came down to three
    1.78 -engines: the Quake II engine, the Source Engine, and jMonkeyEngine.
    1.79 +I examined many different 3D environments to try and find something I
    1.80 +would use as the base for my simulation; eventually the choice came
    1.81 +down to three engines: the Quake II engine, the Source Engine, and
    1.82 +jMonkeyEngine.
    1.83  
    1.84  ** [[http://www.idsoftware.com][Quake II]]/[[http://www.bytonic.de/html/jake2.html][Jake2]]
    1.85  
    1.86 @@ -172,7 +171,7 @@
    1.87  others for about 2 months I settled on jMonkeyEngine. I chose it
    1.88  because it had the most features out of all the open projects I looked
    1.89  at, and because I could then write my code in Clojure, an
    1.90 -implementation of LISP that runs on the JVM...
    1.91 +implementation of LISP that runs on the JVM.
    1.92  
    1.93  
    1.94  
    1.95 @@ -206,4 +205,3 @@
    1.96  
    1.97  
    1.98  
    1.99 -