comparison thesis/cortex.org @ 535:8a5abd51cd4f

add example / discussion per Winston's request.
author Robert McIntyre <rlm@mit.edu>
date Sun, 27 Apr 2014 20:25:22 -0400
parents 39ee58fef9d8
children 0b0fef5e817b
comparison
equal deleted inserted replaced
534:39ee58fef9d8 535:8a5abd51cd4f
2814 experiece path and building a function that can infer complete 2814 experiece path and building a function that can infer complete
2815 sensory experience given only a stream of proprioceptive data. This 2815 sensory experience given only a stream of proprioceptive data. This
2816 /empathy/ function will provide a bridge to use the body centered 2816 /empathy/ function will provide a bridge to use the body centered
2817 action predicates on video-like streams of information. 2817 action predicates on video-like streams of information.
2818 2818
2819 ** Empathy is the process of tracing though \Phi-space 2819 ** Empathy is the process of building paths in \Phi-space
2820 2820
2821 Here is the core of a basic empathy algorithm, starting with an 2821 Here is the core of a basic empathy algorithm, starting with an
2822 experience vector: 2822 experience vector:
2823 2823
2824 An /experience-index/ is an index into the grand experience vector 2824 An /experience-index/ is an index into the grand experience vector
2843 generate a set of similar experiences for each input using the 2843 generate a set of similar experiences for each input using the
2844 tiered proprioceptive bins. 2844 tiered proprioceptive bins.
2845 2845
2846 Finally, to infer sensory data, I select the longest consecutive 2846 Finally, to infer sensory data, I select the longest consecutive
2847 chain of experiences that threads through the sets of similar 2847 chain of experiences that threads through the sets of similar
2848 experiences. Consecutive experience means that the experiences 2848 experiences, starting with the current moment as a root and going
2849 appear next to each other in the experience vector. 2849 backwards. Consecutive experience means that the experiences appear
2850 2850 next to each other in the experience vector.
2851 2851
2852 A stream of proprioceptive input might be:
2853
2854 #+BEGIN_EXAMPLE
2855 [ flat, flat, flat, flat, flat, flat, lift-head ]
2856 #+END_EXAMPLE
2857
2858 The worm's previous experience of lying on the ground and lifting
2859 its head generates possible interpretations for each frame:
2860
2861 #+BEGIN_EXAMPLE
2862 [ flat, flat, flat, flat, flat, flat, flat, lift-head ]
2863 1 1 1 1 1 1 1 4
2864 2 2 2 2 2 2 2
2865 3 3 3 3 3 3 3
2866 7 7 7 7 7 7 7
2867 8 8 8 8 8 8 8
2868 9 9 9 9 9 9 9
2869 #+END_EXAMPLE
2870
2871 These interpretations suggest a new path through phi space:
2872
2873 #+BEGIN_EXAMPLE
2874 [ flat, flat, flat, flat, flat, flat, flat, lift-head ]
2875 6 7 8 9 1 2 3 4
2876 #+END_EXAMPLE
2877
2878 The new path through \Phi-space is synthesized from two actual
2879 paths that the creature actually experiences, the "1-2-3-4" chain
2880 and the "6-7-8-9" chain. The "1-2-3-4" chain is necessary because
2881 it ends with the worm lifting its head. It originated from a short
2882 training session where the worm rested on the floor for a brief
2883 while and then raised its head. The "6-7-8-9" chain is part of a
2884 longer chain of inactivity where the worm simply rested on the
2885 floor without moving. It is preferred over a "1-2-3" chain (which
2886 also describes inactivity) because it is longer. The main ideas
2887 again:
2888
2889 - Imagined \Phi-space paths are synthesized by looping and mixing
2890 previous experiences.
2891
2892 - Longer experience paths (less edits) are preferred.
2893
2894 - The present is more important than the past --- more recent
2895 events take precedence in interpretation.
2852 2896
2853 This algorithm has three advantages: 2897 This algorithm has three advantages:
2854 2898
2855 1. It's simple 2899 1. It's simple
2856 2900