cortex: thesis/cortex.org comparison

comparison thesis/cortex.org @ 536:0b0fef5e817b

more clarification.

author	Robert McIntyre <rlm@mit.edu>
date	Sun, 27 Apr 2014 20:39:33 -0400
parents	8a5abd51cd4f
children	bc5eb476693a

comparison

equal deleted inserted replaced

-:8a5abd51cd4f
+:0b0fef5e817b
 (set (some #(% proprio-data) lookups)))))
 #+end_src
 #+end_listing
 #+caption: =longest-thread= finds the longest path of consecutive
-#+caption: experiences to explain proprioceptive worm data from
+#+caption: past experiences to explain proprioceptive worm data from
 #+caption: previous data. Here, the film strip represents the
 #+caption: creature's previous experience. Sort sequences of
 #+caption: memories are spliced together to match the
 #+caption: proprioceptive data. Their carry the other senses
 #+caption: along with them.
 rest period by looping the one second rest chain five times.
 =longest-thread= takes time proportional to the average number of
 entries in a proprioceptive bin, because for each element in the
 starting bin it performs a series of set lookups in the preceding
-bins. If the total history is limited, then this is only a constant
+bins. If the total history is limited, then this takes time
-multiple times the number of entries in the starting bin. This
+proprotional to a only a constant multiple of the number of entries
-analysis also applies even if the action requires multiple longest
+in the starting bin. This analysis also applies, even if the action
-chains -- it's still the average number of entries in a
+requires multiple longest chains -- it's still the average number
-proprioceptive bin times the desired chain length. Because
+of entries in a proprioceptive bin times the desired chain length.
-=longest-thread= is so efficient and simple, I can interpret
+Because =longest-thread= is so efficient and simple, I can
-worm-actions in real time.
+interpret worm-actions in real time.
 #+caption: Program to calculate empathy by tracing though \Phi-space
 #+caption: and finding the longest (ie. most coherent) interpretation
 #+caption: of the data.
 #+name: longest-thread
 There is one final piece, which is to replace missing sensory data
 with a best-guess estimate. While I could fill in missing data by
 using a gradient over the closest known sensory data points,
 averages can be misleading. It is certainly possible to create an
 impossible sensory state by averaging two possible sensory states.
-Therefore, I simply replicate the most recent sensory experience to
+For example, consider moving your hand in an arc over your head. If
-fill in the gaps.
+for some reason you only have the initial and final positions of
+this movement in your \Phi-space, averaging them together will
+produce the proprioceptive sensation of having your hand /inside/
+your head, which is physically impossible to ever experience
+(barring motor adaption illusions). Therefore I simply replicate
+the most recent sensory experience to fill in the gaps.
 #+caption: Fill in blanks in sensory experience by replicating the most
 #+caption: recent experience.
 #+name: infer-nils
 #+begin_listing clojure
 :experiences experiences})))
 @experiences))
 #+end_src
 #+end_listing
-#+caption: Use longest thread and a phi-space generated from a short
+#+caption: Use =longest-thread= and a \Phi-space generated from a short
 #+caption: exercise routine to interpret actions during free play.
 #+name: empathy-debug
 #+begin_listing clojure
 #+begin_src clojure
 (defn init []
 (cond
 (grand-circle? empathy) (.setText text "Grand Circle")
 (curled? empathy)       (.setText text "Curled")
 (wiggling? empathy)     (.setText text "Wiggling")
 (resting? empathy)      (.setText text "Resting")
-:else                       (.setText text "Unknown")))))))
+:else                   (.setText text "Unknown")))))))
 (defn empathy-experiment [record]
 (.start (worm-world :experience-watch (debug-experience-phi)
 :record record :worm worm*)))
 #+end_src
 #+end_listing
+These programs create a test for the empathy system. First, the
+worm's \Phi-space is generated from a simple motor script. Then the
+worm is re-created in an environment almost exactly identical to
+the testing environment for the action-predicates, with one major
+difference : the only sensory information available to the system
+is proprioception. From just the proprioception data and
+\Phi-space, =longest-thread= synthesises a complete record the last
+300 sensory experiences of the worm. These synthesized experiences
+are fed directly into the action predicates =grand-circle?=,
+=curled?=, =wiggling?=, and =resting?= from before and their output
+is printed to the screen at each frame.
 The result of running =empathy-experiment= is that the system is
 generally able to interpret worm actions using the action-predicates
 on simulated sensory data just as well as with actual data. Figure
 \ref{empathy-debug-image} was generated using =empathy-experiment=:
 accuracy on manual testing of the worm using =init-interactive= and
 =test-empathy-accuracy=. The majority of errors are near the
 boundaries of transitioning from one type of action to another.
 During these transitions the exact label for the action is more open
 to interpretation, and disagreement between empathy and experience
-is more excusable.
+is essentially irrelevant at this point, giving a practical
+identification accuracy of even higher than 95%. When I watch this
-** COMMENT Digression: Learn touch sensor layout through free play
+system myself, I generally see no errors in action identification.
+** COMMENT Digression: Learning touch sensor layout through free play
 In the previous section I showed how to compute actions in terms of
 body-centered predicates which relied on the average touch
 activation of pre-defined regions of the worm's skin. What if,
 instead of receiving touch pre-grouped into the six faces of each

Mercurial > cortex

comparison thesis/cortex.org @ 536:0b0fef5e817b