1.1 --- a/thesis/cortex.org	Fri Apr 25 00:05:46 2014 -0400
     1.2 +++ b/thesis/cortex.org	Sat Apr 26 19:36:13 2014 -0400
     1.3 @@ -41,7 +41,7 @@
     1.4      [[./images/aurellem-gray.png]]
     1.5  
     1.6  
     1.7 -* Empathy \& Embodiment: problem solving strategies
     1.8 +* COMMENT Empathy \& Embodiment: problem solving strategies
     1.9  
    1.10    By the end of this thesis, you will have seen a novel approach to
    1.11    interpreting video using embodiment and empathy. You will also see
    1.12 @@ -415,7 +415,7 @@
    1.13     \end{sidewaysfigure}
    1.14  #+END_LaTeX
    1.15  
    1.16 -* Designing =CORTEX=
    1.17 +* COMMENT Designing =CORTEX=
    1.18  
    1.19    In this section, I outline the design decisions that went into
    1.20    making =CORTEX=, along with some details about its implementation.
    1.21 @@ -2545,7 +2545,7 @@
    1.22    #+end_src
    1.23    #+end_listing
    1.24  
    1.25 -** Embodiment factors action recognition into manageable parts
    1.26 +** COMMENT Embodiment factors action recognition into manageable parts
    1.27  
    1.28     Using empathy, I divide the problem of action recognition into a
    1.29     recognition process expressed in the language of a full compliment
    1.30 @@ -2574,13 +2574,13 @@
    1.31     =grand-circle?= relies on touch and reuses =curled?= in its
    1.32     definition, showing how embodied predicates can be composed.
    1.33     
    1.34 +   
    1.35     #+caption: Program for detecting whether the worm is curled. This is the 
    1.36     #+caption: simplest action predicate, because it only uses the last frame 
    1.37     #+caption: of sensory experience, and only uses proprioceptive data. Even 
    1.38     #+caption: this simple predicate, however, is automatically frame 
    1.39 -   #+caption: independent and ignores vermopomorphic \begin{footnote} Like 
    1.40 -   #+caption: \emph{anthropomorphic}, except for worms instead of humans.
    1.41 -   #+caption: \end{footnote} differences such as worm textures and colors.
    1.42 +   #+caption: independent and ignores vermopomorphic\protect\footnotemark  
    1.43 +   #+caption: differences such as worm textures and colors.
    1.44     #+name: curled
    1.45     #+begin_listing clojure
    1.46     #+begin_src clojure
    1.47 @@ -2593,6 +2593,10 @@
    1.48     (:proprioception (peek experiences))))
    1.49     #+end_src
    1.50     #+end_listing
    1.51 +   
    1.52 +   #+BEGIN_LaTeX
    1.53 +   \footnotetext{Like \emph{anthropomorphic} except for worms instead of humans.}
    1.54 +   #+END_LaTeX
    1.55  
    1.56     #+caption: Program for summarizing the touch information in a patch 
    1.57     #+caption: of skin.
    1.58 @@ -2744,7 +2748,7 @@
    1.59     sensory data on which they depend is absent. If I can do that, then
    1.60     I will have gained much.
    1.61  
    1.62 -** \Phi-space describes the worm's experiences
    1.63 +** COMMENT \Phi-space describes the worm's experiences
    1.64     
    1.65     As a first step towards building empathy, I need to gather all of
    1.66     the worm's experiences during free play. I use a simple vector to
    1.67 @@ -2790,7 +2794,7 @@
    1.68     provided by an experience vector and reliably inferring the rest of
    1.69     the senses.
    1.70  
    1.71 -** Empathy is the process of tracing though \Phi-space 
    1.72 +** COMMENT Empathy is the process of tracing though \Phi-space 
    1.73  
    1.74     Here is the core of a basic empathy algorithm, starting with an
    1.75     experience vector:
    1.76 @@ -2951,7 +2955,7 @@
    1.77     #+end_src
    1.78     #+end_listing
    1.79    
    1.80 -** =EMPATH= recognizes actions efficiently
    1.81 +** COMMENT =EMPATH= recognizes actions efficiently
    1.82     
    1.83     To use =EMPATH= with the worm, I first need to gather a set of
    1.84     experiences from the worm that includes the actions I want to
    1.85 @@ -3107,7 +3111,7 @@
    1.86    to interpretation, and disagreement between empathy and experience
    1.87    is more excusable.
    1.88  
    1.89 -** Digression: Learn touch sensor layout through free play
    1.90 +** COMMENT Digression: Learn touch sensor layout through free play
    1.91  
    1.92     In the previous section I showed how to compute actions in terms of
    1.93     body-centered predicates which relied on the average touch
    1.94 @@ -3269,7 +3273,7 @@
    1.95     completely scrambled. The cross shape is just for convenience. This
    1.96     example justifies the use of pre-defined touch regions in =EMPATH=.
    1.97  
    1.98 -* Contributions
    1.99 +* COMMENT Contributions
   1.100    
   1.101    In this thesis you have seen the =CORTEX= system, a complete
   1.102    environment for creating simulated creatures. You have seen how to
   1.103 @@ -3307,7 +3311,7 @@
   1.104  \appendix
   1.105  #+END_LaTeX
   1.106  
   1.107 -* Appendix: =CORTEX= User Guide
   1.108 +* COMMENT Appendix: =CORTEX= User Guide
   1.109  
   1.110    Those who write a thesis should endeavor to make their code not only
   1.111    accessible, but actually usable, as a way to pay back the community