|
rlm@513
|
1 @@ -3234,8 +3354,8 @@
|
|
rlm@513
|
2
|
|
rlm@513
|
3 - =CORTEX=, a system for creating simulated creatures with rich
|
|
rlm@513
|
4 senses.
|
|
rlm@513
|
5 - - =EMPATH=, a program for recognizing actions by imagining sensory
|
|
rlm@513
|
6 - experience.
|
|
rlm@513
|
7 + - =EMPATH=, a program for recognizing actions by aligning them with
|
|
rlm@513
|
8 + personal sensory experiences.
|
|
rlm@513
|
9
|
|
rlm@513
|
10 # An anatomical joke:
|
|
rlm@513
|
11 # - Training
|
|
rlm@515
|
12
|
|
rlm@515
|
13 @@ -2732,7 +2851,7 @@
|
|
rlm@515
|
14 provided by an experience vector and reliably infering the rest of
|
|
rlm@515
|
15 the senses.
|
|
rlm@515
|
16
|
|
rlm@515
|
17 -** Empathy is the process of tracing though \Phi-space
|
|
rlm@515
|
18 +** ``Empathy'' requires retracing steps though \Phi-space
|
|
rlm@515
|
19
|
|
rlm@515
|
20 Here is the core of a basic empathy algorithm, starting with an
|
|
rlm@515
|
21 experience vector:
|
|
rlm@515
|
22 @@ -2440,7 +2558,8 @@
|
|
rlm@515
|
23 hard control problems without worrying about physics or
|
|
rlm@515
|
24 senses.
|
|
rlm@515
|
25
|
|
rlm@515
|
26 -* Empathy in a simulated worm
|
|
rlm@515
|
27 +* =EMPATH=: the simulated worm experiment
|
|
rlm@515
|
28 +# Empathy in a simulated worm
|
|
rlm@515
|
29
|
|
rlm@515
|
30 Here I develop a computational model of empathy, using =CORTEX= as a
|
|
rlm@515
|
31 base. Empathy in this context is the ability to observe another
|
|
rlm@516
|
32
|
|
rlm@516
|
33 @@ -436,7 +554,7 @@
|
|
rlm@516
|
34 doing everything in software is far cheaper than building custom
|
|
rlm@516
|
35 real-time hardware. All you need is a laptop and some patience.
|
|
rlm@516
|
36
|
|
rlm@516
|
37 -** Because of Time, simulation is perferable to reality
|
|
rlm@516
|
38 +** Simulated time enables rapid prototyping and complex scenes
|
|
rlm@516
|
39
|
|
rlm@516
|
40 I envision =CORTEX= being used to support rapid prototyping and
|
|
rlm@516
|
41 iteration of ideas. Even if I could put together a well constructed
|
