cortex: thesis/cortex.org comparison

comparison thesis/cortex.org @ 525:25f23cfd56ce

alter pics, enhance text.

author	Robert McIntyre <rlm@mit.edu>
date	Mon, 21 Apr 2014 02:13:23 -0400
parents	1e51263afdc0
children	96c189d4d15e

comparison

equal deleted inserted replaced

-:8e52a2802821
+:25f23cfd56ce
 * Empathy \& Embodiment: problem solving strategies
 By the end of this thesis, you will have seen a novel approach to
-interpreting video using embodiment and empathy. You will have also
+interpreting video using embodiment and empathy. You will also see
-seen one way to efficiently implement empathy for embodied
+one way to efficiently implement physical empathy for embodied
 creatures. Finally, you will become familiar with =CORTEX=, a system
-for designing and simulating creatures with rich senses, which you
+for designing and simulating creatures with rich senses, which I
-may choose to use in your own research.
+have designed as a library that you can use in your own research.
+Note that I /do not/ process video directly --- I start with
+knowledge of the positions of a creature's body parts and works from
+there.
 This is the core vision of my thesis: That one of the important ways
 in which we understand others is by imagining ourselves in their
 position and emphatically feeling experiences relative to our own
 bodies. By understanding events in terms of our own previous
 would otherwise be an unwieldy exponential search. This extra
 constraint can be the difference between easily understanding what
 is happening in a video and being completely lost in a sea of
 incomprehensible color and movement.
-** The problem: recognizing actions in video is hard!
+** The problem: recognizing actions is hard!
 Examine the following image. What is happening? As you, and indeed
 very young children, can easily determine, this is an image of
 drinking.
 probabilities than with recognizing various affordances: things you
 can move, objects you can grasp, spaces that can be filled . For
 example, what processes might enable you to see the chair in figure
 \ref{hidden-chair}?
-#+caption: The chair in this image is quite obvious to humans, but I
+#+caption: The chair in this image is quite obvious to humans, but
-#+caption: doubt that any modern computer vision program can find it.
+#+caption: it can't be found by any modern computer vision program.
 #+name: hidden-chair
 #+ATTR_LaTeX: :width 10cm
 [[./images/fat-person-sitting-at-desk.jpg]]
 Finally, how is it that you can easily tell the difference between
 saved for later use. It is harder to conduct science because it is
 harder to repeat an experiment. The worst thing about using the
 real world instead of a simulation is the matter of time. Instead
 of simulated time you get the constant and unstoppable flow of
 real time. This severely limits the sorts of software you can use
-to program the AI because all sense inputs must be handled in real
+to program an AI, because all sense inputs must be handled in real
 time. Complicated ideas may have to be implemented in hardware or
 may simply be impossible given the current speed of our
 processors. Contrast this with a simulation, in which the flow of
 time in the simulated world can be slowed down to accommodate the
 limitations of the character's programming. In terms of cost,
 cochlea; each one is sensitive to a slightly different frequency of
 sound. For eyes, it is rods and cones distributed along the surface
 of the retina. In each case, we can describe the sense with a
 surface and a distribution of sensors along that surface.
-The neat idea is that every human sense can be effectively
+In fact, almost every human sense can be effectively described in
-described in terms of a surface containing embedded sensors. If the
+terms of a surface containing embedded sensors. If the sense had
-sense had any more dimensions, then there wouldn't be enough room
+any more dimensions, then there wouldn't be enough room in the
-in the spinal chord to transmit the information!
+spinal chord to transmit the information!
 Therefore, =CORTEX= must support the ability to create objects and
 then be able to ``paint'' points along their surfaces to describe
 each sense.
 (movement-kernel creature muscle)))
 #+END_SRC
 #+end_listing
-=movement-kernel= creates a function that will move the nearest
+=movement-kernel= creates a function that controlls the movement
-physical object to the muscle node. The muscle exerts a rotational
+of the nearest physical node to the muscle node. The muscle exerts
-force dependent on it's orientation to the object in the blender
+a rotational force dependent on it's orientation to the object in
-file. The function returned by =movement-kernel= is also a sense
+the blender file. The function returned by =movement-kernel= is
-function: it returns the percent of the total muscle strength that
+also a sense function: it returns the percent of the total muscle
-is currently being employed. This is analogous to muscle tension
+strength that is currently being employed. This is analogous to
-in humans and completes the sense of proprioception begun in the
+muscle tension in humans and completes the sense of proprioception
-last section.
+begun in the last section.
 ** =CORTEX= brings complex creatures to life!
 The ultimate test of =CORTEX= is to create a creature with the full
 gamut of senses and put it though its paces.
 - Inverse kinematics :: experiments in sense guided motor control
 are easy given =CORTEX='s support -- you can get right to the
 hard control problems without worrying about physics or
 senses.
+\newpage
 * =EMPATH=: action recognition in a simulated worm
 Here I develop a computational model of empathy, using =CORTEX= as a
 base. Empathy in this context is the ability to observe another
 creature and infer what sorts of sensations that creature is
 free-play, where the creature moves around and gains sensory
 experience. From this experience I construct a representation of the
 creature's sensory state space, which I call \Phi-space. Using
 \Phi-space, I construct an efficient function which takes the
 limited data that comes from observing another creature and enriches
-it full compliment of imagined sensory data. I can then use the
+it with a full compliment of imagined sensory data. I can then use
-imagined sensory data to recognize what the observed creature is
+the imagined sensory data to recognize what the observed creature is
 doing and feeling, using straightforward embodied action predicates.
 This is all demonstrated with using a simple worm-like creature, and
 recognizing worm-actions based on limited data.
 #+caption: Here is the worm with which we will be working.
 ** Action recognition is easy with a full gamut of senses
 Embodied representations using multiple senses such as touch,
 proprioception, and muscle tension turns out be be exceedingly
-efficient at describing body-centered actions. It is the ``right
+efficient at describing body-centered actions. It is the right
-language for the job''. For example, it takes only around 5 lines
+language for the job. For example, it takes only around 5 lines of
-of LISP code to describe the action of ``curling'' using embodied
+LISP code to describe the action of curling using embodied
 primitives. It takes about 10 lines to describe the seemingly
 complicated action of wiggling.
 The following action predicates each take a stream of sensory
 experience, observe however much of it they desire, and decide
 whether the worm is doing the action they describe. =curled?=
 relies on proprioception, =resting?= relies on touch, =wiggling?=
 relies on a Fourier analysis of muscle contraction, and
-=grand-circle?= relies on touch and reuses =curled?= as a guard.
+=grand-circle?= relies on touch and reuses =curled?= in its
+definition, showing how embodied predicates can be composed.
 #+caption: Program for detecting whether the worm is curled. This is the
 #+caption: simplest action predicate, because it only uses the last frame
 #+caption: of sensory experience, and only uses proprioceptive data. Even
 #+caption: this simple predicate, however, is automatically frame
-#+caption: independent and ignores vermopomorphic differences such as
+#+caption: independent and ignores vermopomorphic \footnote{Like
-#+caption: worm textures and colors.
+#+caption: \emph{anthropomorphic}, except for worms instead of humans.}
+#+caption: differences such as worm textures and colors.
 #+name: curled
 #+begin_listing clojure
 #+begin_src clojure
 (defn curled?
 "Is the worm curled up?"
 will work regardless of whether the worm is a different color or
 heavily textured, or if the environment has strange lighting.
 The trick now is to make the action predicates work even when the
 sensory data on which they depend is absent. If I can do that, then
-I will have gained much,
+I will have gained much.
 ** \Phi-space describes the worm's experiences
 As a first step towards building empathy, I need to gather all of
 the worm's experiences during free play. I use a simple vector to

Mercurial > cortex

comparison thesis/cortex.org @ 525:25f23cfd56ce